search_snippets

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

No annotations, so the description carries the behavioral burden. It usefully guarantees output is verbatim and never rewritten and includes a citation, but says nothing about permissions, scope, or limits. Since an output schema exists, the return-shape burden is lighter.

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?

Purpose is front-loaded, and the Args block cleanly follows. Slightly emphatic with capitalized VERBATIM and dash clauses, but each sentence carries useful content.

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 two-param search tool with an output schema, the description covers purpose, use cases, and both parameters adequately. The only real gap is not positioning itself against sibling search tools.

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 0%, so the description must compensate, and it does: it explains query as a keyword/phrase with concrete examples ('TGF-beta fibrosis') and top_k as the count of notes to pull from, with the default. Both parameters get meaning beyond the bare schema titles.

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+resource: 'return the VERBATIM source sentence from each of the most relevant notes, with its citation.' This distinguishes it in substance from a whole-note reader, but it never names the obvious sibling (search_notes) to anchor the distinction.

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 positive use cases ('what does the literature say about X', 'a factor's role'), which implies context. But with many search siblings (search_notes, search_articles, search_figures, search_grouped) it never says when to prefer this over them, so routing is left to inference.

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