Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds behavioral details beyond those: it returns a list (not a single item), it is verifiable/cryptographically signed, and it implies a subsequent singular call for full detail. It does not contradict annotations and enriches the agent's understanding of the tool's output behavior.

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 somewhat long but each sentence earns its place: it states the purpose, contrasts with aggregators, lists filters with an example, and provides usage guidance. The key purpose is front-loaded. It could be trimmed slightly, but overall it is well-structured and not redundant.

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 search tool with 8 parameters and no output schema, the description covers the main functionality, filter options, and result handling (returns a list, then call singular for detail). It doesn't explicitly mention pagination, but offset/limit are in the schema. The 'verifiable' note adds trust context. Everything essential for calling the tool is present.

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 schema has descriptions for 6 of 8 parameters (75% coverage), leaving limit and offset undocumented. The description names several filters (race_key, state, subject, pollster, since) with examples, which adds semantic clarity over the raw schema. However, it does not cover the undocumented limit/offset or clarify the cycle parameter. Since coverage is just below 80% and the description partially compensates but not fully, a 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 starts with a specific verb and resource: 'Search the SIGNED public-poll archive.' It immediately distinguishes itself from aggregators by emphasizing exact question wording and full methodological details, which sets it apart from sibling search tools like politics_search or politics_bills_search. The purpose is unambiguous and context-rich.

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 explicitly states when to use this tool: 'Use this when a question hinges on what a poll ACTUALLY asked vs how it was reported.' It also provides a clear next-step routing: 'Returns a list; call politics_poll {id} for full detail + signature,' which guides the agent to the singular sibling. This is excellent usage direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.