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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds genuinely non-obvious behavior: a one-to-three minute latency with a long-timeout recommendation, unanswerable questions returning 200 with chart null and specific reason strings, warning/detail blocks on engine failure, and quote-tracing fallback. That is substantial context the annotations cannot express.

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?

The critical scoping rule and the 'use it whenever' trigger are front-loaded, and nearly every sentence earns its place (latency, error bodies, tag normalization, stable id). It is a single dense block, though, and the long enumeration of 400 validation cases could be tightened without losing meaning.

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 slow, permission-scoped, non-destructive query tool with no output schema, the description covers everything an agent needs: output shape, latency expectations, permission model, scoping via meetingId/tags, idempotency key usage, and the full failure taxonomy with status codes. Nothing material 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 coverage is 100%, so the baseline would be 3, but the description adds real semantics: meetingId comes from List Meetings (meetings[].id), tags match meetings carrying any of those tags or topic names, tags are normalized (trim, uppercase, spaces/underscores to dashes) and ignored when meetingId is set, and id is stable per question+meetingId. These are matching rules the schema cannot convey.

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 ('answers a plain-language question from the company's processed meetings') and names the output shape (headline, short answer, optional chart, quotes). It is clearly distinguishable from siblings like list_meetings or search_liliphant_docs, which find meetings/docs rather than synthesize answers.

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 trigger ('use it whenever someone asks what was said, decided or promised') and an explicit scoping rule: omit meetingId to search everything the asker may see, set it to answer from one meeting only. It also states who may call it and what each role can see, which resolves the main ambiguity an agent would face.

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