politics_pollGet one poll in full: pollster, sponsor, field dates, population, sample size, margin of error, mode, the VERBATIM question(s) asked, per-option toplines, the first-party source_url, and the signature (poll_proof) that binds the exact wording and numbers. This is the ground truth to check any claim about a poll against.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Poll ID from politics_polls results |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context beyond that: it lists the full set of returned fields, including the poll_proof signature, and states the tool's role as ground truth, which helps the agent trust and interpret results.
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 dense sentence that front-loads the verb and resource, then lists all included data in a clear sequence. No wasted words; every clause adds meaning.
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 tool with one simple parameter and no output schema, the description fully covers what the agent needs to know: what is returned, the source, and how to use it. Nothing critical is missing.
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 single parameter (id) is fully described in the schema as 'Poll ID from politics_polls results', so the description adds no additional parameter semantics. With 100% schema coverage, the baseline of 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 states a specific verb ('Get') and resource ('one poll in full') and enumerates exactly what fields are returned, distinguishing it from list-style siblings like politics_polls. The 'ground truth' phrasing further clarifies its unique role.
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?
Context is clear: this tool retrieves full poll details, implying use when a poll ID is known and complete data is needed. It does not explicitly name alternatives or exclusions, but the 'ground truth' framing signals when to prefer this over other poll-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 has a clearly distinct purpose covering different aspects of political data: bills (search, details, text slices, TOC), officials (details, search, by state, representation), bridge pages (create, compare, session, letter), and specialized queries (speeches, votes, positions, provenance). No two tools overlap in functionality.
All tools follow a consistent 'politics_<descriptive_name>' pattern using snake_case. Verbs and nouns are combined logically (e.g., 'politics_bills_search', 'politics_candidate_feed'), with no mixing of conventions.
At 25 tools, the set is comprehensive for a political data API but slightly on the high side. However, each tool covers a specific niche (bills, officials, bridge pages, etc.), and the count is justified by the breadth of the domain. It remains manageable and well-scoped.
The tool surface covers major data types (bills, officials, candidates, speeches, votes, positions) and interaction workflows (bridge pages, watchlists). Minor gaps exist, such as missing a direct 'politician by name and state' endpoint, but the search and filtering tools compensate. Overall, the set is thorough.