Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Washington State Legislature MCP Server What's the status of HB 1234?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that provides AI assistants with access to Washington State Legislature data, enabling civic engagement through conversational interfaces.
This MCP server connects AI assistants to the Washington State Legislative Web Services (WSLWS), providing tools for:
Bill tracking and information retrieval
Committee meeting schedules and agendas
Legislator lookup and sponsor information
Bill status and history tracking
Legislative document access
Related MCP server: OpenDiscourse MCP
getBillInfo - Retrieve detailed information about specific bills
searchBills - Search for bills using keywords and optional filtering
getBillsByYear - Retrieve all bills from a specific year with filtering options
getCommitteeMeetings - Get committee meeting schedules and agendas
findLegislator - Find legislators by district or lookup sponsors
getBillStatus - Get current status and history of a bill
getBillDocuments - Retrieve bill document metadata with links
getBillContent - Retrieve the actual content of a bill in AI-friendly format
bill://xml/{biennium}/{chamber}/{bill_number} - Access bill documents in structured XML format
bill://htm/{biennium}/{chamber}/{bill_number} - Access bill documents in HTML format
bill://pdf/{biennium}/{chamber}/{bill_number} - Get URLs for bill PDF documents
bill://document/{format}/{biennium}/{chamber}/{bill_number} - Generic format for accessing bill documents
Python 3.10+
pip package manager
pip install -e ".[dev]"pip install .# Test with MCP Inspector
mcp dev src/wa_leg_mcp/server.py
# Run with stdio transport
python src/wa_leg_mcp/server.pyFor cloud deployment on AWS Lambda, you can use the mcp-remote adapter to enable Claude Desktop connectivity:
{
"mcpServers": {
"wa-leg": {
"command": "npx",
"args": [
"mcp-remote",
"https://your-api-gateway-url/sse"
]
}
}
}Create a .env file:
WSL_API_TIMEOUT=30
WSL_CACHE_TTL=300
LOG_LEVEL=INFO
SERVER_NAME="Washington State Legislature MCP Server"wa-leg-mcp/
├── src/
│ ├── wa_leg_mcp/
│ │ ├── __init__.py
│ │ ├── server.py # Main MCP server implementation
│ │ ├── tools/ # Tool implementations
│ │ │ ├── __init__.py
│ │ │ ├── bill_tools.py
│ │ │ ├── committee_tools.py
│ │ │ └── legislator_tools.py
│ │ ├── resources/ # MCP resource implementations
│ │ │ ├── __init__.py
│ │ │ └── bill_resources.py # Bill document resources
│ │ ├── clients/ # API clients
│ │ │ ├── __init__.py
│ │ │ └── wsl_client.py # WA State Legislature API client
│ │ └── utils/ # Utility functions
│ │ ├── __init__.py
│ │ └── formatters.py
├── tests/ # Test suite
│ ├── __init__.py
│ ├── test_bill_tools.py
│ ├── test_bill_resources.py # Tests for bill resources
│ ├── test_committee_tools.py
│ ├── test_legislator_tools.py
│ ├── test_server.py
│ ├── test_utils_formatters.py
│ └── test_wsl_client.py
├── pyproject.toml # Project configuration and dependencies
├── Makefile # Development workflow commands
├── README.md
└── LICENSEClone the repository:
git clone https://github.com/awalcutt/wa-leg-mcp.git
cd wa-leg-mcpCreate virtual environment:
python -m venv venv
source venv/bin/activate # Or `venv\Scripts\activate` on WindowsInstall development dependencies:
pip install -e ".[dev]"Run tests:
make testCreate a new file in src/wa_leg_mcp/tools/
Implement tool using the MCP decorator:
from mcp.server.fastmcp import Tool
@Tool("toolName", description="Tool description")
def tool_function(param1: str, param2: str = None):
# Implementation
return {"result": data}Register tool in server.py by adding it to the get_default_tools() function
Add tests in tests/
Run directly with Python
Use with MCP Inspector for development
AWS Lambda with API Gateway (supports remote connections via mcp-remote adapter)
Google Cloud Functions
Azure Functions
Variable | Description | Default |
| API request timeout (seconds) | 30 |
| Cache time-to-live (seconds) | 300 |
| Logging level | INFO |
| Custom server name | Washington State Legislature MCP Server |
Add to Claude Desktop configuration:
{
"mcpServers": {
"wa-leg": {
"command": "python",
"args": ["path/to/src/wa_leg_mcp/server.py"],
"env": {
"WSL_CACHE_TTL": "600"
}
}
}
}# Example client integration
from mcp.client import ClientSession
import asyncio
async def connect_to_legislature_mcp():
async with ClientSession(server_command=["python", "src/wa_leg_mcp/server.py"]) as session:
# List available tools
tools = await session.list_tools()
# Call a tool
result = await session.call_tool("getBillInfo", {
"bill_number": "HB1234",
"biennium": "2025-26"
})
print(result)
# Access a resource
bill_xml = await session.read_resource(
"bill://xml/2025-26/House/1234"
)
print(f"Bill XML content length: {len(bill_xml)}")
asyncio.run(connect_to_legislature_mcp())Retrieves detailed information about a specific bill using the GetLegislation API.
Parameters:
bill_number (string, required): Bill number (e.g., "HB1234", "SB5678")
biennium (string, required): Legislative biennium in format "2025-26"
Returns: Bill details including description, sponsor, status, fiscal notes, and companions
Searches for bills using keywords and optional filtering via the WSL Search API.
Parameters:
query (string, required): Search query text (e.g., "climate change", "transportation")
bienniums (array, optional): List of bienniums to search (format: "YYYY-YY"), defaults to current
agency (string, optional): Filter by originating agency ("House", "Senate", or "Both")
max_results (integer, optional): Maximum number of total results to return (max 100)
Returns: List of bills matching the search criteria
Retrieves all bills from a specific year with optional filtering using the GetLegislationByYear API.
Parameters:
year (string, optional): Year in format "YYYY" (e.g., "2025"), defaults to current
agency (string, optional): Filter by originating agency ("House" or "Senate")
active_only (boolean, optional): If True, only return active bills
Returns: List of bills matching the criteria
Retrieves committee meetings and agendas using the GetCommitteeMeetings API.
Parameters:
start_date (string, required): Start date in YYYY-MM-DD format
end_date (string, required): End date in YYYY-MM-DD format
committee (string, optional): Filter by specific committee
Returns: List of committee meetings with dates, times, locations, and agenda items
Finds legislators using the GetSponsors API.
Parameters:
biennium (string, required): Legislative biennium in format "2025-26"
chamber (string, optional): "house" or "senate"
Returns: List of legislators with ID, name, party, and contact information
Gets current status and history using the GetCurrentStatus API.
Parameters:
bill_number (string, required): Bill number (e.g., "HB1234")
biennium (string, required): Legislative biennium in format "2025-26"
Returns: Current status, history, action dates, and status descriptions
Retrieves bill documents metadata (functionality based on Document service endpoints).
Parameters:
bill_number (string, required): Bill number
biennium (string, required): Legislative biennium in format "2025-26"
document_type (string, optional): "bill", "amendment", "report"
Returns: Document metadata with links to HTML and PDF versions
Retrieves the actual content of a bill in an AI-friendly format.
Parameters:
bill_number (integer, required): Bill number as an integer (e.g., 1234 for HB1234)
biennium (string, optional): Legislative biennium in format "2025-26" (defaults to current)
chamber (string, optional): Chamber name - "House" or "Senate" (optional if bill_number is unique across chambers)
bill_format (string, optional): Document format - "xml" (default), "htm", or "pdf"
Returns: For XML and HTM formats: Dict containing the document content and metadata. For PDF format: Dict containing the URL to access the PDF and metadata.
The MCP server provides direct access to bill documents through URI templates:
Access bill documents in structured XML format (recommended for AI processing).
Parameters:
biennium (string): Legislative biennium in format "YYYY-YY" (e.g., "2025-26")
chamber (string): Chamber name - must be exactly "House" or "Senate"
bill_number (string): Bill number as numeric string (e.g., "1234")
Returns: XML content of the bill document
Access bill documents in HTML format with hyperlinks to referenced laws.
Parameters:
biennium (string): Legislative biennium in format "YYYY-YY"
chamber (string): "House" or "Senate"
bill_number (string): Bill number
Returns: HTML content of the bill document
Get URLs for bill PDF documents (content not fetched).
Parameters:
biennium (string): Legislative biennium in format "YYYY-YY"
chamber (string): "House" or "Senate"
bill_number (string): Bill number
Returns: Dictionary with URL to access the PDF document
Generic format for accessing bill documents in any supported format.
Parameters:
format (string): Document format - "xml", "htm", or "pdf"
biennium (string): Legislative biennium in format "YYYY-YY"
chamber (string): "House" or "Senate"
bill_number (string): Bill number
Returns: Document content or URL based on format
We welcome contributions! Please see our Contributing Guidelines for details.
This project is licensed under the MIT License - see the LICENSE file for details.
Find legislators (sponsors) for a specific biennium, optionally filtered by chamber and/or district.
Args: biennium: Legislative biennium in format "2025-26" (optional, defaults to current) chamber: Filter by chamber ("house" or "senate") (optional) district: Filter by legislative district number (optional)
Returns: Dict containing list of legislators matching the criteria
| Name | Required | Description | Default |
|---|---|---|---|
| biennium | No | ||
| chamber | No | ||
| district | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must cover behavior. It specifies return type (dict with list) but lacks details on pagination, errors, or side effects. Basic but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is very concise with a clear structure: main action, then bullet-pointed args, then return info. No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers the essential purpose and parameters but could be more precise (e.g., specifying chamber values as literal 'house' or 'senate', and district as integer). Still adequate for a simple tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but the description adds clear meaning for all three parameters: biennium (default current), chamber (house/senate), district (number). This fully compensates for the schema gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it finds legislators (sponsors) for a given biennium with optional filters, distinguishing it from sibling tools that handle bills or committee meetings.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explains the parameters and defaults but does not explicitly guide when to use this tool versus alternatives like search_bills. No when-not-to-use or alternative mentions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve the content of a bill in an AI-friendly format.
This tool fetches the actual content of a bill document, defaulting to XML format which is most suitable for AI processing due to its structured nature. It can also return HTML content or a link to the PDF version.
Args: bill_number: Bill number as an integer (e.g., 1234 for HB1234, 5678 for SB5678) biennium: Legislative biennium in format "YYYY-YY" (e.g., "2025-26") (optional, defaults to current) chamber: Chamber name - "House" or "Senate" (optional if bill_number is unique across chambers) bill_format: Document format - "xml" (default), "htm", or "pdf"
Returns: For XML and HTM formats: Dict containing the document content and metadata For PDF format: Dict containing the URL to access the PDF and metadata
Note: This tool complements the get_bill_documents tool, which provides metadata about available documents. This tool provides the actual content of the bill.
When citing bill content in responses, consider including a link to the PDF version
using the format: https://lawfilesext.leg.wa.gov/biennium/{biennium}/Pdf/Bills/{chamber}%20Bills/{bill_number}.pdf
| Name | Required | Description | Default |
|---|---|---|---|
| bill_number | Yes | ||
| biennium | No | ||
| chamber | No | ||
| bill_format | No | xml |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Discloses default format, optional parameters, and behavior for different formats. Explains chamber optionality and includes example bill_number usage. No annotations present, so description carries full burden and meets it well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with sections for args, returns, and notes. However, slightly verbose with details like PDF link format. Still effective and not overly long.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers all aspects: purpose, parameters, returns, and citation guidance. Has output schema but description still adds value. No gaps identified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Despite 0% schema description coverage, the description provides clear, detailed explanations for each parameter: bill_number with example, biennium format, chamber as string, bill_format options. Adds significant meaning beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it retrieves bill content in AI-friendly format, specifies default XML format, and distinguishes from sibling get_bill_documents which provides metadata.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly states when to use (need actual content) and when not (metadata via get_bill_documents). Also advises on citation and PDF link usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve bill documents including bill text and amendments.
Args: bill_number: Bill number as an integer (e.g., 1234 for HB1234, 5678 for SB5678) biennium: Legislative biennium in format "YYYY-YY" (e.g., "2025-26") (optional, defaults to current) document_type: Filter by type - "bill", "amendment", "report" (optional)
Returns: Dict containing document metadata with links to HTML and PDF versions
Note: This tool returns metadata about available documents. To get the actual content of a bill in AI-friendly format, use the get_bill_content tool.
| Name | Required | Description | Default |
|---|---|---|---|
| bill_number | Yes | ||
| biennium | No | ||
| document_type | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It discloses that it returns metadata with links to HTML and PDF, and explains the document_type filter. However, it does not mention error handling or behavior for missing bills, but is otherwise clear.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two well-structured paragraphs with clear sections (summary, Args, Returns, Note). Every sentence adds value; no fluff. Front-loaded with purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the existence of an output schema, the description adequately explains parameters and return type. Covers purpose, parameters, and usage note. No missing critical information for a metadata retrieval tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema description coverage, the description adds critical meaning: explains bill_number format (e.g., 1234 for HB1234), biennium format and default, and document_type allowed values ('bill', 'amendment', 'report'). Fully compensates for schema gaps.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states 'Retrieve bill documents including bill text and amendments' with a specific verb and resource. It distinguishes from sibling tool get_bill_content by noting that this tool returns metadata, not actual content.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Provides explicit guidance: 'To get the actual content of a bill in AI-friendly format, use the get_bill_content tool.' This tells the agent when not to use this tool and gives an alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve detailed information about a specific bill.
Args: bill_number: Bill number as an integer (e.g., 1234 for HB1234, 5678 for SB5678) biennium: Legislative biennium in format "YYYY-YY" (e.g., "2025-26") (optional, defaults to current)
Returns: Dict containing bill details including description, sponsor, status, etc.
| Name | Required | Description | Default |
|---|---|---|---|
| bill_number | Yes | ||
| biennium | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the burden of behavioral disclosure. It correctly notes that biennium is optional and defaults to current. However, it fails to mention read-only nature, error handling, or any side effects. The return format is described as a dict, which adds some transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and follows a clear docstring structure with Args and Returns. Every sentence serves a purpose, and there is no redundant information. It earns its place efficiently.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given two parameters and an output schema, the description is largely complete. Parameter semantics are well-explained, and the return type is mentioned. However, it could list specific keys in the returned dict for better completeness, but since output schema exists, this is less critical.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so the description must compensate. It provides examples for bill_number (e.g., 1234 for HB1234) and the format for biennium. This adds significant meaning beyond the schema. However, it could include validation or default behavior for missing biennium.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states it retrieves detailed information about a specific bill. Although it lists the return fields, it does not explicitly distinguish from siblings like get_bill_status or get_bill_content. However, the verb 'retrieve detailed information' and the mention of 'description, sponsor, status, etc.' clearly indicate the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided about when to use this tool versus alternatives. The description only explains the parameters but does not offer comparative usage advice or prerequisites. For a tool with many siblings, this lack of context could confuse agents.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve all bills from a specific year with optional filtering.
This function retrieves all legislation for a year and allows filtering by agency (House or Senate) and active status.
Args: year: Year in format "YYYY" (e.g., "2025") (optional, defaults to current) agency: Filter by originating agency ("House" or "Senate") (optional) active_only: If True, only return active bills
Returns: Dict containing list of bills matching the criteria
| Name | Required | Description | Default |
|---|---|---|---|
| year | No | ||
| agency | No | ||
| active_only | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It describes retrieval and filtering, implying a safe read operation. However, it lacks details on potential side effects, rate limits, or any authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is well-structured with a clear short description and docstring format for arguments and returns. It is concise but could omit the docstring style for even more brevity.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple retrieval tool with three optional parameters and an output schema, the description covers the essential functionality. It explains what the return value contains (dict with list of bills), which is sufficient given the output schema exists.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has no descriptions for parameters (coverage 0%). The description fully explains each parameter: year format, agency values ('House' or 'Senate'), and active_only boolean. This adds significant meaning beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it retrieves all bills from a specific year with optional filtering. However, it does not differentiate from sibling tools like search_bills, which might also retrieve bills.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives like search_bills or get_bill_info. The description does not include any when-to-use or when-not-to-use criteria.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get the current status and history of a specific bill.
Args: bill_number: Bill number as an integer (e.g., 1234 for HB1234, 5678 for SB5678) biennium: Legislative biennium in format "YYYY-YY" (e.g., "2025-26") (optional, defaults to current)
Returns: Dict containing current status and history
| Name | Required | Description | Default |
|---|---|---|---|
| bill_number | Yes | ||
| biennium | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries full burden. It only states 'Returns: Dict containing current status and history' without disclosing read-only nature, auth requirements, rate limits, or any side effects. More detail needed for safe agent invocation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Description is concise with three logical sections: purpose, Args, Returns. Every sentence adds value, no fluff. Purpose is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given output schema exists, minimal return info is acceptable. Description covers both parameters adequately for usage. Could marginally improve by noting bill number prefix convention more explicitly, but overall sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, but description adds comprehensive semantics: bill_number is explained with examples (e.g., 1234 for HB1234) and type clarification; biennium gets format example and default value explanation. Adds significant value beyond schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Description clearly states verb+resource: 'Get the current status and history of a specific bill.' It distinguishes from sibling tools like get_bill_content and get_bills_by_year, though it could be more explicit about difference from get_bill_info.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description provides parameter details but no guidance on when to use this tool versus alternatives. No when-to-use or when-not-to-use context, and no reference to siblings like get_bill_info which might be confused.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieve committee meetings and agendas.
Args: start_date: Start date in YYYY-MM-DD format end_date: End date in YYYY-MM-DD format committee: Filter by specific committee (optional)
Returns: Dict containing list of committee meetings
| Name | Required | Description | Default |
|---|---|---|---|
| start_date | Yes | ||
| end_date | Yes | ||
| committee | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description must carry the burden of behavioral disclosure. It only describes the basic retrieval operation and return type, but omits details like authentication needs, rate limits, side effects, or whether data is live or cached.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, using a clear header and bullet-style Args/Returns sections. Every sentence adds value, and the main purpose is front-loaded, making it easy to scan.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The tool has an output schema, so the description need not elaborate return structure beyond a dict of meetings. It mentions agendas, which is helpful. However, it lacks any discussion of date range limits, pagination, or error handling. Still, for a simple retrieval tool, it is mostly complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 0% description coverage, so the description fills the gap by listing each parameter with format (e.g., YYYY-MM-DD for dates) and indicating optionality. This adds meaningful value beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool retrieves committee meetings and agendas, using a specific verb and resource. It distinguishes itself from sibling tools which focus on bills and legislators, making purpose unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or restrictions. The description simply states the action without contextual usage advice.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Simple health check to verify the server is running.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Without annotations, the description carries the burden of behavioral disclosure. It implies a simple, non-destructive check but does not specify what 'health check' entails (e.g., response format, latency implications). The presence of an output schema partially compensates, but more context would be beneficial.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, well-structured sentence that immediately conveys the tool's purpose. It is concise and front-loaded, with no wasted words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter health check tool, the description is nearly complete. It clearly states the purpose. However, it could mention that it is safe to call repeatedly or that it returns a simple status, but given the output schema existence, the current description is adequate.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, and schema coverage is 100%. The description adds no parameter semantics because none are needed. Baseline 4 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Simple health check to verify the server is running' clearly states the tool's purpose with a specific verb and resource. It effectively distinguishes from sibling tools like 'find_legislator' or 'search_bills' which are data retrieval operations, not connectivity checks.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description does not provide any guidance on when to use this tool versus alternatives, nor does it mention prerequisites or when not to use it. For a health check tool, it would be helpful to note that it should be called before other operations to verify server availability, but this is absent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for bills using keywords and optional filtering.
This function uses the WSL Search API to find bills matching the provided query with optional filtering by biennium and agency.
Args: query: Search query text (e.g., "climate change", "transportation") bienniums: List of bienniums to search (format: "YYYY-YY") (optional, defaults to current) agency: Filter by originating agency ("House", "Senate", or "Both") (optional, defaults to "Both") max_results: Maximum number of total results to return (max 100)
Returns: Dict containing list of bills matching the search criteria
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | ||
| bienniums | No | ||
| agency | No | ||
| max_results | No |
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations provided, so description carries the burden. It mentions using the 'WSL Search API' and returns a 'Dict containing list of bills,' but lacks details on pagination, rate limits, or error handling. Adequate but not comprehensive.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Well-structured with a one-line summary, then args list and returns. The Args section is slightly redundant with schema but adds value. No wasted sentences.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given an output schema exists (flagged true), the description provides sufficient context for a search tool. It covers query, filters, and result type, fitting well among sibling tools.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 0%, so description must add meaning. It provides examples for query, explains biennium format, agency options, and max_results limit, which significantly enhances the schema's minimal info.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description 'Search for bills using keywords and optional filtering' clearly states the verb (search) and resource (bills), distinguishing it from sibling tools like get_bill_info or get_bills_by_year.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Description lists optional filters but does not explicitly state when to use this tool versus alternatives like get_bills_by_year. Implicit usage is clear, but no when-not-to guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0find_legislatorget_bill_contentget_bill_documentsget_bill_infoget_bill_statusget_bills_by_yearget_committee_meetingspingsearch_billsEach tool targets a distinct aspect of legislative data: legislators, bill content, bill metadata, bill details, bill status, committee meetings, search, and health check. Descriptions clearly differentiate purposes with no overlap.
Tools consistently use snake_case with verb_noun pattern (e.g., get_bill_content, search_bills), except for 'ping' which is a standard health check but deviates. Overall pattern is clear.
9 tools are well-scoped for a legislative information server, covering search, retrieval of details, documents, status, legislators, and committee meetings without being bloated or sparse.
The set covers core legislative needs such as bills, legislators, committees, and search. Missing advanced features like committee member lists or law code retrieval, but sufficient for typical use.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Search bills and speaker-attributed hearing transcripts across all 50 US state legislatures.
U.S. civic data for AI agents: reps, votes, bills, finance, lobbying, cited gov sources. 47 tools.
Search bills, legislators, committees, and events across all 50 US states, DC, and 5 US territories.
U.S. federal policy data — bills, Congress members, voting records, and civic info.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/awalcutt/wa-leg-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
