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

Annotations cover the safety profile (readOnlyHint false, destructiveHint false, idempotentHint false), and the description adds context those flags cannot: it returns a job handle immediately rather than minutes, costs 2 credits per run, and crucially guarantees the source speaker-separation job is 'never changed or deleted'. The async/credit/reversibility details are exactly the behavioral traits an agent needs beyond structured hints.

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 action and async return are front-loaded, followed by input routing, output contents, and cost/guarantees in a tight sequence. It is dense but each sentence carries distinct information; only the enumeration of minute contents is mildly long.

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?

There is no output schema, so the description correctly takes on the burden of describing what the minutes contain (summary, decisions, action items with owners/deadlines, speaker attribution, timestamps, open questions). Combined with the async job pattern, cost, and non-destructive guarantee, an agent has everything needed to call this correctly.

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 adds value by characterizing meetingNotes as pasted text, clarifying sourceJobId points at a completed speaker_separation job whose labeled transcript is reused without re-upload, and previewing the minute contents. It doesn't add format/syntax detail beyond the schema, so it sits just above baseline.

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 opening sentence gives a specific verb and resource ('Start a meeting-minutes job') and immediately frames it as an async job that returns a handle, which distinguishes it from synchronous siblings like get_job. It also names the sibling tool (speaker_separation) it can consume input from, so an agent can separate it from adjacent tools 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?

It states the two mutually exclusive input routes (meetingNotes OR sourceJobId) and directs the agent to get_job for retrieval, and explains the condition that makes sourceJobId valid ('a completed speaker_separation job in this organization — no re-upload'). It does not spell out when-not-to-use this tool versus any alternative summarization path, so it stops short of the top score.

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