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

Annotations already cover read-only and idempotent safety, so the description adds useful behavior beyond them: exact output fields, the fact that it returns only top hits, lack of advanced options, and the fetch integration. It doesn't mention result limits, but the output schema already reduces that gap.

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 sentences with no filler: the first states purpose and output upfront, the second routes to the alternative. Every phrase earns its place, including the integration hint with fetch.

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 one-parameter read-only search with an output schema, the description is complete. It covers what the tool returns, the compatibility contract, the alternative for richer needs, and the relationship to fetch. Nothing necessary for correct invocation 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?

Schema coverage is 100% and the single query parameter already has a clear description ('A single query string'). The tool description doesn't add extra query syntax or formatting details, so the schema carries the semantic weight; a 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 names the operation ('search over the corpus'), the output shape ('top hits as {id, title, url}'), and the defining trait ('OpenAI-compatible', 'id is the cite anchor fetch accepts'). It also differentiates itself from search_legislation, so an agent can select the right tool without opening schemas.

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?

It explicitly says when not to use this tool: 'For filters, snippets, scores and paging use search_legislation'. The mention of the citation-compatible id also implies the intended use with fetch, giving both an inclusion and exclusion context.

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