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

Annotations already cover the safety profile (readOnly, idempotent, not open-world), so the bar is lower; the description still adds useful behavior, namely the return shape (best-matching sections with snippet plus URL and anchor) and the language-scoping model. It stops short of explaining result ranking or how limit truncation behaves.

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?

Three sentences, zero filler: scope and return value first, follow-up tool second, language caveat last. Every sentence carries information an agent needs.

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?

With an output schema present, the description needn't detail return values, and it covers scope, language, and the handoff to get_page. The one remaining gap is disambiguation against get_pricing/list_pages, which matters more here than return detail.

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 query, lang, limit and section are all documented in the schema itself. The description only restates the language default ('English by default; pass lang for the French or German site') without adding format or syntax guidance beyond it, so the baseline 3 applies.

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 across aidata.stream') and enumerates the exact corpus covered: docs, blog, changelog, pricing, FAQ, home. It also distinguishes itself from the sibling get_page by positioning search as the discovery step and page-reading as the follow-up.

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?

Explicitly tells the agent what to do next ('Use get_page to read a whole page afterwards') and clarifies the language default with an escape hatch. It does not say when to prefer get_pricing or list_pages over a search, so routing among all four siblings is only partially covered.

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