get_approval

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

Annotations only declare readOnlyHint and openWorldHint; the description adds the required messages:read scope, 404 semantics for missing or cross-agent ids, the expires_at-to-expired behavior, and the polling contract. It also enumerates every returned field in the absence of an output schema.

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 purpose and polling rule, then auth scope, then return fields. The full field enumeration is long but justified because there is no output schema; only the exhaustive list keeps it from a 5.

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 supplies the return shape, status enumeration, auth requirement, polling behavior, and failure mode. Nothing material is missing for correct invocation.

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 explains approval_id, so the baseline is 3. The description adds value by tying the id to request_approval's return and by documenting the 404 failure mode for nonexistent or foreign-agent ids.

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 (fetch) and resource (approval request by id) and ties it to the sibling that creates it, request_approval. An agent can distinguish it from request_approval, get_message, and the other siblings without opening a 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?

Explicitly instructs to call it after request_approval, to re-call with a pause while status is pending, and to treat anything but approved as no. That is concrete when-to-use and how-to-poll guidance, not inference.

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