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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds real substance beyond that: keyless source, 2016-to-next-meeting coverage, and the non-obvious empty-state behavior ('says so with the meeting date and FDA's posting timeline instead of returning an empty list'). It also flags that include_questions_text triggers an extra PDF fetch. It omits rate limits/response size for a potentially large PDF-aggregating call, which keeps it at 4 rather than 5.

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 core question, and the trigger-phrase and pairing clauses each earn their place for retrieval and routing. The middle sentence is a long run-on enumerating return fields, which is dense and could be broken into a short list, but there is no 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 5-optional-parameter, read-only aggregation tool with no output schema, the description fully carries the return-shape burden: document metadata fields, extracted agenda text, applications under review, docket, webcast, and voting questions. The empty-result contract and source provenance are both stated, leaving nothing an agent needs 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?

With 100% schema coverage the schema already documents every parameter with examples, so the baseline is 3. The description adds the combinational selection model that the schema only implies — filters are applied 'by committee..., by date, and/or by drug, sponsor or topic' to converge on a single meeting — plus the default of one best-match meeting.

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 precise verb and resource up front ('What evidence is an FDA advisory committee reviewing?') and enumerates exactly what comes back — briefing documents, agenda, questions, rosters, slides, minutes, transcripts, docket, webcast, voting questions. It explicitly separates itself from fda_adcom_calendar and pdufa_catalysts, so an agent can distinguish it from siblings without opening any 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?

Names the two adjacent tools and their distinct roles ('fda_adcom_calendar (which meetings are coming) and pdufa_catalysts (the decision date that follows the panel)'), which is explicit alternative routing. It also supplies a keyword trigger list ('AdCom briefing document, FDA briefing book, advisory committee materials, ODAC questions...') covering the phrasings an agent would encounter.

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