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

Annotations only say destructive and idempotent; the description goes far beyond by explaining that seated participants are paid in full from the hold, that spent_usd can rise until results show complete, that the unused hold is returned, and that a cancel is irreversible. This is exactly the financial and irreversibility context an agent needs before invoking a destructive tool.

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 is front-loaded in the first two words, followed by consequences, then usage, then an example — a sensible order with no filler sentences. There is minor duplication of structured data (repeating that idempotent repeat changes nothing, and describing the return value despite an output schema).

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 one-parameter destructive tool with full annotations and an output schema, the description covers consequences, irreversibility, and money handling thoroughly. The remaining gap is that call_id provenance is never explained, leaving the agent to infer it from sibling tools.

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 0% for the single call_id parameter, so the schema supplies only a bare string type. The description partially compensates with the example {"call_id": "call_..."}, which hints at the accepted format, but it never states what a call_id is or where the agent obtains one.

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?

'Stops a call' is a specific verb and resource, and the body spells out what stopping means operationally (no new participants rung, seated participants finish). It does not explicitly contrast itself with siblings like ask_people_send_outcome, so the boundary is left implicit, but the operation is unmistakable.

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 gives a clear trigger — the user says the answers in hand suffice or the task changed — plus a useful implied exclusion that a call closes by itself at its deadline, so no cancel is needed. Alternatives are not named, but the when-to-use condition is concrete.

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