search_policiesSearch U.S. federal policies and legislation by keyword, topic, or bill name. Returns a list of matching policies with summaries.
| Name | Required | Description | Default |
|---|---|---|---|
| sort | No | Sort order | importance |
| limit | No | Number of results (max 25) | |
| query | Yes | Search query (bill name, topic, keyword) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotation readOnlyHint=true already indicates a safe read operation, and the description is consistent. It adds that results are 'a list of matching policies with summaries,' which is useful output-shape context. However, it does not mention sorting, limiting, pagination, or error behavior, but the schema covers parameter defaults.
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 sentence that is concise and front-loaded with the verb and resource. It includes the key search facets and the return value in exactly 20 words, with no redundant phrasing. It earns its place without 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 simple search tool, the description covers the purpose, search criteria, and return type. The schema handles parameter specifics, and the annotation covers read-only safety. No output schema exists, but the description addresses the return shape. Minor omissions like sort/limit behavior are already in the schema, so the description is sufficiently 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?
Schema description coverage is 100%, so every parameter (query, sort, limit) is already documented with types, enums, defaults, and min/max. The description's mention of 'keyword, topic, or bill name' aligns with the query parameter but adds no new information. Given high schema coverage, baseline 3 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 uses the specific verb 'Search' and clearly identifies the resource as 'U.S. federal policies and legislation,' with explicit search criteria (keyword, topic, bill name). It also states the return type (list of policies with summaries), making its purpose distinct from sibling get_* tools that retrieve individual entities.
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 implies when to use this tool—when searching by keyword, topic, or bill name—but does not explicitly mention alternatives or exclusions. For example, it does not say to use get_policy when a policy ID is already known, or get_policy_text for full text. The context is clear but lacks explicit differentiation from related tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct resource or action: efforts, members, policies, stories, representatives, voter info, and text retrieval. Even similar tools like get_effort and resolve_effort clearly differ in input type (ID vs natural language), and get_stories vs get_story follow the standard list/detail distinction.
All tool names follow a consistent verb_noun pattern using lower_snake_case: get_ for retrieval, search_ for queries, and resolve_ for name resolution. Nouns are clear and descriptive, with no mixing of styles or inconsistent verbs.
With 12 tools, the set is well-scoped for a U.S. political policy tracking service. Each tool provides a distinct utility without overwhelming the surface, fitting solidly within the expected range.
The tool surface covers the core read-only workflows: searching and retrieving policies and members, resolving and retrieving efforts, listing and retrieving story bundles, and looking up representatives and voter info. There are no obvious gaps or dead ends for the stated purpose.