AI Agents · Lesson

Designing Shareable Agent Tools

Tool schema standards, documentation requirements, and packaging for reuse.

Designing Shareable Agent Tools is a free AI Agents lesson on CoddyKit — lesson 1 of 4. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the AI Agents learning path, one of 4 lessons in the course, and your progress syncs across the web and the CoddyKit app.

What Makes a Tool Shareable?

A shareable agent tool is one that other developers can drop into their agent systems without reading the source code. It has a clear, machine-readable schema, a human-readable README, well-defined error codes, and predictable behaviour. Think of it as a library, not a script.

Tool Schema Standards

Every shareable tool must have a schema describing its inputs, outputs, and metadata. The schema is the contract between the tool author and the agent using it. Base it on JSON Schema for maximum compatibility with all major agent frameworks.

TOOL_SCHEMA_TEMPLATE = {
    'name': 'get_weather',
    'description': 'Returns current weather conditions for a city. '
                   'Use when the user asks about weather or temperature.',
    'version': '1.2.0',
    'parameters': {
        'type': 'object',
        'properties': {
            'city': {
                'type': 'string',
                'description': 'City name (e.g., London, Tokyo)',
                'minLength': 1,
                'maxLength': 100
            },
            'units': {
                'type': 'string',
                'enum': ['celsius', 'fahrenheit'],
                'default': 'celsius',
                'description': 'Temperature unit'
            }
        },
        'required': ['city']
    },
    'returns': {
        'type': 'object',
        'properties': {
            'temperature': {'type': 'number'},
            'condition': {'type': 'string'},
            'humidity_pct': {'type': 'number'}
        }
    },
    'rate_limit': {'calls_per_minute': 60}
}

if __name__ == '__main__':
    print(f"Tool: {TOOL_SCHEMA_TEMPLATE['name']} (v{TOOL_SCHEMA_TEMPLATE['version']})")
    print('Description:', TOOL_SCHEMA_TEMPLATE['description'])
    print('Required params:', TOOL_SCHEMA_TEMPLATE['parameters']['required'])

Error Codes

Define a standard error response format. Every tool should return the same error structure: code, message, and optional details. This lets the agent handle errors programmatically without knowing tool internals.

from enum import Enum

class ToolErrorCode(Enum):
    INVALID_PARAMS = 'INVALID_PARAMS'
    NOT_FOUND = 'NOT_FOUND'
    RATE_LIMITED = 'RATE_LIMITED'
    UPSTREAM_ERROR = 'UPSTREAM_ERROR'
    TIMEOUT = 'TIMEOUT'
    UNAUTHORISED = 'UNAUTHORISED'
    INTERNAL_ERROR = 'INTERNAL_ERROR'

class ToolError(Exception):
    def __init__(self, code: ToolErrorCode, message: str, details: dict = None):
        self.code = code
        self.message = message
        self.details = details or {}

    def to_dict(self) -> dict:
        return {
            'error': True,
            'code': self.code.value,
            'message': self.message,
            'details': self.details
        }

try:
    raise ToolError(
        ToolErrorCode.NOT_FOUND,
        'City not found in database',
        {'city': 'Atlantis', 'suggestion': 'Did you mean Athens?'}
    )
except ToolError as e:
    print(e.to_dict())

Input Validation

Validate inputs against the schema before execution. Use jsonschema for automatic validation. Fail fast with a descriptive error rather than letting invalid inputs cause cryptic failures deep in the tool logic.

import jsonschema  # pip install jsonschema

def validate_tool_input(params: dict, schema: dict) -> dict:
    """
    Validate params against schema.
    Returns validated (and default-filled) params.
    Raises ToolError on validation failure.
    """
    try:
        # Fill in defaults
        filled = dict(params)
        for prop, definition in schema['properties'].items():
            if prop not in filled and 'default' in definition:
                filled[prop] = definition['default']

        # Validate against schema
        jsonschema.validate(instance=filled, schema=schema)
        return filled

    except jsonschema.ValidationError as e:
        raise ToolError(
            ToolErrorCode.INVALID_PARAMS,
            f'Validation failed: {e.message}',
            {'path': list(e.path), 'schema_path': list(e.schema_path)}
        )

# Example usage:
try:
    params = validate_tool_input({'city': 'London'}, TOOL_SCHEMA_TEMPLATE['parameters'])
    print('Valid params:', params)
except ToolError as e:
    print('Error:', e.to_dict())

Usage Examples in the Schema

Add concrete examples to your tool schema. Examples serve two purposes: they help humans understand the tool quickly, and they can be injected into the agent's context as few-shot demonstrations to improve tool call accuracy.

TOOL_WITH_EXAMPLES = {
    'name': 'search_knowledge_base',
    'description': 'Search the company knowledge base for documentation.',
    'parameters': {
        'type': 'object',
        'properties': {
            'query': {'type': 'string'},
            'top_k': {'type': 'integer', 'default': 5, 'minimum': 1, 'maximum': 20}
        },
        'required': ['query']
    },
    'examples': [
        {
            'description': 'Search for onboarding docs',
            'input': {'query': 'how to onboard new users', 'top_k': 3},
            'output': {'results': [{'title': 'User Onboarding Guide', 'score': 0.95}]}
        },
        {
            'description': 'Search with default top_k',
            'input': {'query': 'API authentication'},
            'output': {'results': [{'title': 'API Auth Docs', 'score': 0.88}]}
        }
    ]
}

if __name__ == '__main__':
    print('Tool:', TOOL_WITH_EXAMPLES['name'])
    for ex in TOOL_WITH_EXAMPLES['examples']:
        print(f" - {ex['description']}: input={ex['input']} -> output={ex['output']}")

Rate Limiting in Tools

Tools that call external APIs must respect rate limits. Implement a per-tool rate limiter using a token bucket or sliding window. Return a standard RATE_LIMITED error with retry-after seconds when the limit is exceeded.

import time
from collections import deque

class SlidingWindowRateLimiter:
    def __init__(self, max_calls: int, window_seconds: int):
        self.max_calls = max_calls
        self.window = window_seconds
        self._calls = deque()  # timestamps of recent calls

    def check(self) -> tuple:
        """
        Returns (allowed: bool, retry_after_seconds: float)
        """
        now = time.time()
        # Remove calls outside the window
        while self._calls and self._calls[0] < now - self.window:
            self._calls.popleft()

        if len(self._calls) >= self.max_calls:
            oldest = self._calls[0]
            retry_after = (oldest + self.window) - now
            return False, round(retry_after, 1)

        self._calls.append(now)
        return True, 0.0

weather_limiter = SlidingWindowRateLimiter(max_calls=10, window_seconds=60)
allowed, retry = weather_limiter.check()
if not allowed:
    raise ToolError(ToolErrorCode.RATE_LIMITED,
                    f'Rate limit exceeded. Retry in {retry}s',
                    {'retry_after': retry})

Packaging as a Python Package

Structure your tool as an installable Python package so other developers can add it to their agents with a single pip install. The package exposes a get_tool_definition() function and an execute(params) function as the public API.

# Directory structure:
# agent_tool_weather/
#   __init__.py
#   tool.py
#   schema.py
#   pyproject.toml
#   README.md

# agent_tool_weather/tool.py
from .schema import SCHEMA
from .errors import ToolError, ToolErrorCode

def get_tool_definition() -> dict:
    return SCHEMA

def execute(params: dict) -> dict:
    validated = validate_tool_input(params, SCHEMA['parameters'])
    city = validated['city']
    units = validated['units']
    return _fetch_weather(city, units)

def _fetch_weather(city: str, units: str) -> dict:
    import requests
    url = f'https://api.weather.example.com/current?city={city}&units={units}'
    response = requests.get(url, headers={'X-API-Key': 'YOUR_KEY'}, timeout=5)
    if response.status_code == 404:
        raise ToolError(ToolErrorCode.NOT_FOUND, f'City not found: {city}')
    response.raise_for_status()
    return response.json()

Writing the Tool README

A clear README is essential for adoption. Include: what the tool does, installation command, required API keys or credentials, all parameters with types and defaults, all error codes, and at least one complete usage example.

README_TEMPLATE = '''
# agent-tool-weather

Get real-time weather conditions for any city.

## Installation

pip install agent-tool-weather

## Setup

import os
os.environ["WEATHER_API_KEY"] = "your-key-here"

## Usage

from agent_tool_weather import get_tool_definition, execute

# In your agent
tool_def = get_tool_definition()

# Execute
result = execute({"city": "Tokyo", "units": "celsius"})
print(result)
# {"temperature": 22.5, "condition": "Partly cloudy", "humidity_pct": 65}

## Parameters

| Name  | Type   | Required | Default  | Description     |
|-------|--------|----------|----------|-----------------|
| city  | string | Yes      | -        | City name       |
| units | string | No       | celsius  | celsius or fahrenheit |

## Error Codes

- INVALID_PARAMS: Parameter validation failed
- NOT_FOUND: City not found
- RATE_LIMITED: 60 calls/minute limit exceeded
- UPSTREAM_ERROR: Weather API unavailable
'''

print(README_TEMPLATE[:300])

Testing a Shareable Tool

A shareable tool must have automated tests covering: happy path, each error code, edge cases (empty strings, max values), and rate limiting behaviour. Tests are documentation — they show exactly how the tool behaves.

import pytest

def test_valid_city_returns_weather(mock_weather_api):
    result = execute({'city': 'London'})
    assert 'temperature' in result
    assert 'condition' in result
    assert isinstance(result['temperature'], (int, float))

def test_missing_required_param_raises_error():
    with pytest.raises(ToolError) as exc_info:
        execute({})  # city is required
    assert exc_info.value.code == ToolErrorCode.INVALID_PARAMS

def test_unknown_city_raises_not_found(mock_weather_api_404):
    with pytest.raises(ToolError) as exc_info:
        execute({'city': 'Atlantis'})
    assert exc_info.value.code == ToolErrorCode.NOT_FOUND

def test_default_units_is_celsius():
    params = validate_tool_input({'city': 'Paris'}, TOOL_SCHEMA_TEMPLATE['parameters'])
    assert params['units'] == 'celsius'

def test_rate_limit_enforced():
    limiter = SlidingWindowRateLimiter(max_calls=2, window_seconds=60)
    limiter.check()  # call 1
    limiter.check()  # call 2
    allowed, _ = limiter.check()  # call 3 — should fail
    assert not allowed

OpenAI Function-Calling Compatible Format

For compatibility with OpenAI and Claude's native tool-use APIs, ensure your tool schema is in the exact format those APIs expect. The get_openai_schema() method converts your internal schema to the OpenAI-compatible format.

def get_openai_schema(tool_schema: dict) -> dict:
    """Convert internal tool schema to OpenAI function-calling format."""
    return {
        'type': 'function',
        'function': {
            'name': tool_schema['name'],
            'description': tool_schema['description'],
            'parameters': tool_schema['parameters']
        }
    }

def get_anthropic_schema(tool_schema: dict) -> dict:
    """Convert to Anthropic tool format."""
    return {
        'name': tool_schema['name'],
        'description': tool_schema['description'],
        'input_schema': tool_schema['parameters']
    }

# Usage in an agent:
openai_tools = [get_openai_schema(t) for t in [TOOL_SCHEMA_TEMPLATE]]
anthropic_tools = [get_anthropic_schema(t) for t in [TOOL_SCHEMA_TEMPLATE]]
print('OpenAI format:', openai_tools[0]['function']['name'])
print('Anthropic format:', anthropic_tools[0]['name'])

Versioning Your Tool

Use semantic versioning: MAJOR.MINOR.PATCH. Increment MAJOR on breaking schema changes, MINOR when adding optional parameters, PATCH for bug fixes. Store version in the schema and expose it via get_tool_definition().

VERSION = '1.2.0'

def bump_version(current: str, change_type: str) -> str:
    parts = list(map(int, current.split('.')))
    if change_type == 'major':
        return f'{parts[0]+1}.0.0'
    if change_type == 'minor':
        return f'{parts[0]}.{parts[1]+1}.0'
    if change_type == 'patch':
        return f'{parts[0]}.{parts[1]}.{parts[2]+1}'
    raise ValueError(f'Unknown change_type: {change_type}')

# Breaking change (removed required param) -> major
print(bump_version('1.2.0', 'major'))  # 2.0.0
# Added optional param -> minor
print(bump_version('1.2.0', 'minor'))  # 1.3.0
# Bug fix -> patch
print(bump_version('1.2.0', 'patch'))  # 1.2.1

Knowledge Check

Which part of a shareable tool schema allows the agent framework to automatically validate inputs before calling the tool's execution function?

Recap: Designing Shareable Agent Tools

Key takeaways from this lesson:

Schema: name, description, version, parameters (JSON Schema), returns, rate_limit
Error codes: standard ToolError with code, message, details
Input validation: jsonschema validates against parameters schema before execution
Examples: included in schema as few-shot context
Rate limiting: sliding window with RATE_LIMITED error and retry_after
Packaging: pip-installable package with README, tests, and versioning

Next: plugin discovery and dynamic tool loading.

Frequently asked questions

Is the “Designing Shareable Agent Tools” lesson free?

Yes — the full text of “Designing Shareable Agent Tools” is free to read here on the web, and the AI Agents course includes 4 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the AI Agents course, upgrade to CoddyKit PRO.

What will I learn in “Designing Shareable Agent Tools”?

Tool schema standards, documentation requirements, and packaging for reuse. You practise AI Agents with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.

Do I need any experience to start AI Agents?

No prior experience is required. AI Agents on CoddyKit is structured for beginners through advanced learners; this is — lesson 1 of 4, so you can start here or from the beginning and move at your own pace.

How long does the “Designing Shareable Agent Tools” lesson take?

Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.

Can I write and run code in this AI Agents lesson?

Yes. Every AI Agents lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.

All lessons in this course

← Back to AI Agents