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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds substantive behavior beyond them: whole-word-prefix matching, accent sensitivity with a concrete counterexample, ordering ('newest first'), and result provenance ('canonical URL to cite'). Pagination mechanics are disclosed precisely, including that nextCursor is absent on the last page.

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?

Front-loaded with purpose and scope, then matching semantics, then the sibling routing rule, then pagination. Every sentence carries operational information; even the accent example ('Male' does not find 'Malé') is a compact, high-value warning rather than filler.

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 7-parameter search tool with a full output schema, the description covers everything an agent needs to call it correctly: scope, matching rules, ordering, pagination continuation, and where to go when results are empty. Return-value details are correctly left to the output schema, with only the citation-relevant field called out.

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%, so the baseline is 3, but the description adds real semantics on top: it clarifies the matching rules for q and explains cursor continuation ('same arguments, limit may differ'), which reinforces the schema's caveat. It does not restate the date-range or section-slug meaning beyond the schema, keeping it at 4 rather than 5.

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?

States a specific verb and resource ('Full-text search of published GMM news articles'), names the searched fields (title, summary, body), and immediately scopes what is excluded (partner content). It also explicitly separates itself from search_site, so an agent can pick between the two without opening a schema.

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?

Gives an explicit routing rule: use search_site for a forgiving search or when coverage of First Light, entity records, projects, documents and tracker pages is needed. It also notes partner content is excluded, so the agent knows a null result may mean 'out of scope' rather than 'nonexistent'.

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