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

Annotations cover safety (readOnly, idempotent, non-destructive), so the description is free to add real behavioral context: ranking is best-match-first, results are filtered to aging papers by default, each hit carries study type/aging linkage/subjects/story, and critically that the corpus is not all of PubMed so a null result is not proof of absence. That coverage caveat is exactly the kind of non-obvious behavior an agent needs.

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 the trigger and corpus, then filters, then caveats and the sibling pointer. The long list of example topics is verbose but serves a real disambiguation purpose; the whole thing is a single dense block that would read better split into short sentences.

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 12-parameter search tool with no output schema, it covers the essentials an agent needs: scope, default filtering, syntax, result contents, corpus limits, and the follow-up tool. It does not explain pagination/cursor beyond the schema, but nothing required to call it correctly 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 description coverage is 100%, so the baseline is 3. The description groups the available filters (study type, category, body system, link to aging, preprint status, author, date added) and restates query syntax, which aids scanning but adds little beyond what the schema already documents per parameter.

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 (search) over a specific corpus (titles and abstracts of every paper AgingResearch.News has read) and explicitly separates itself from get_paper for full-text reading. The domain enumeration plus the 'often without the word aging' prompt helps the agent recognize this tool even when the user's phrasing never says 'aging'.

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 a clear triggering condition ('when the user asks what research has found'), explicit exclusions ('Not for personal medical advice, symptoms or product recommendations'), and names the follow-up sibling (get_paper). It also routes the agent correctly when the user's question lacks the word 'aging'.

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