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

Annotations only declare readOnlyHint and idempotentHint; the description adds substantial behavior beyond them: the error_code RESULT_NOT_AVAILABLE path, the L402_REFUND_ISSUED refund flow via paymentId, the audiobook refund recovery at /recover, the uncollected web-3D-purchase case, the ~1 hour URL expiry with 'download immediately', and the fact that the tool is free. This is exactly the extra context annotations cannot carry.

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?

It is front-loaded with the core action and precondition before the enumeration, and every sentence carries actionable content — return shapes, error codes, refund routing, and URL expiry. The length is driven by the real number of jobType/refund branches rather than padding.

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 must carry return-value semantics, and it does so per jobType with concrete field names. Combined with the refund/error branches and expiry warning, nothing an agent needs to call and interpret this tool 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 is 3, but the description goes further: it maps each jobType value to a concrete return shape and explains the conditional role of paymentId in refund handling (payer gets the pending refund only when it matches). That adds genuine call-shaping meaning beyond the schema text.

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 first sentence states a specific verb and resource: 'Retrieve the final output of a completed async job.' It distinguishes itself from the sibling check_job_status by referencing the completion precondition, and the closing sentence excludes synchronous tools. An agent can tell exactly what this tool returns versus its neighbors.

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 an explicit precondition ('Call ONLY after check_job_status returns status=COMPLETED') with the consequence of violating it (returns an error), and an explicit exclusion ('Do NOT use for synchronous tools'). The alternative check_job_status is named, so the when-to-use branch is fully determined.

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