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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's value is the fallback semantics it discloses: a human-edited report takes precedence over the AI-generated one. That is real behavior an agent could not get from the annotations; it does not, however, say what happens when neither version exists.

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?

A single front-loaded sentence carries the resource, the fallback rule, and the accepted identifier forms; nothing is redundant or padded.

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 no output schema, the description partially compensates by naming the two possible report variants, but it never describes what a report contains or the empty/not-found case. For a one-parameter read tool this is adequate, though not exhaustive.

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% and the schema already documents that meetingId accepts a meetingId, an _id, or a shared interview link. The description restates meetingId/_id but actually adds less than the schema by omitting the shared-link form, so it stays at the baseline rather than adding meaning.

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?

The description gives a specific verb and resource ('Get the interview report of a meeting') and adds a precedence rule (human-edited version when one exists, otherwise the AI-generated one) that tells the agent exactly what artifact it will receive. It implicitly separates itself from get_meeting and get_meeting_transcript, though it never names those siblings explicitly.

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?

Usage is implied by the resource name: fetch a report rather than a raw meeting or transcript. There is no explicit when-to-use, when-not-to-use, or named alternative (e.g., 'use get_meeting_transcript for the raw transcript'), so the agent must infer routing from sibling names alone.

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