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

Annotations already cover safety (idempotentHint=true, destructiveHint=false), so the bar is lower; the description still adds real behavior: the completed-run gate and the refusal for unfinished/failed/cancelled runs. It also discloses the link-expiry trait ("the link stops working at expires_at, so fetch it now"), which is a time-sensitive behavior not expressible in annotations. The specific return fields are already carried by the output schema, so that portion is redundant.

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 short sentences, each earning its place: capability, routing/precondition, then return-and-expiry warning. The most decision-relevant information (bulk ZIP, completed-only) is front-loaded.

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?

An output schema exists, so return-value documentation is not required, and annotations cover the safety profile. Combined with the explicit precondition and expiry warning, an agent has everything needed to select and call this tool 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% and both required parameters (workflow_id, run_id) are documented in-schema with sourcing hints ("from run_workflow or list_runs", "from list_workflows. Never invent one"). The description adds no additional parameter meaning beyond the schema, so the baseline of 3 applies.

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 and resource — fetching a single ZIP link containing every audio file from a run — and implicitly contrasts with the sibling get_run_outputs by positioning it as a bulk alternative to per-line downloads. An agent can distinguish it from get_run_outputs, get_run_status and list_runs 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?

Gives an explicit preference rule ("Use this instead of downloading lines one at a time") and an explicit precondition with its failure mode ("Only completed runs can be exported; an unfinished, failed or cancelled run is refused"). Both the when-to-use and when-not-to-use cases are covered.

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