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

Annotations already declare readOnly, idempotent and non-destructive, so the bar is lower; the description still adds state semantics the annotations cannot express, namely that pending or unconfirmed is neither a finished result nor a refund and that resubmission must be avoided. It does not describe the returned settlement shape, which keeps it below a 5.

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?

Three sentences, zero filler, with the no-side-effect guarantee and the recovery trigger front-loaded before the handle-passing instructions. Every clause carries operational information.

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 and no required parameters, the description covers the recovery trigger, both valid input combinations, and the safety constraints. The only gap is what the returned result and settlement actually contain, which would help an agent interpret the response.

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 already 100%, so the baseline is 3; the description earns extra credit by explaining the two alternative identification modes (original clientRequestId alone, or the exact accepted statusUrl/responseUrl/receiptId set) and stressing the handles must be the accepted, unchanged ones. That is meaningful semantics the schema's per-field text only partially conveys.

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?

Uses a specific verb and resource ('read the saved audio result and settlement') and explicitly negates the nearest sibling by stating it works 'without starting generation' after a soclo_audio_make call. An agent can separate this from soclo_audio_make and soclo_audio_poll on the description alone.

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?

Gives a clear trigger ('after an interruption or unknown outcome') and tells the caller not to submit again. It does not name soclo_audio_poll as the alternative for a still-running job, so the recover-vs-poll boundary is left implicit.

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