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

With readOnlyHint already set, the description still adds substantial context beyond annotations: no playback side effect occurs here, the URLs are short-lived and must not be cached, and the per-entry output shape is disclosed. These are operationally important traits not captured by the structured fields.

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?

Every sentence earns its place: purpose, precondition, safety guard, output shape, and caching warning. The critical precondition is front-loaded right after the purpose.

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 read tool with full schema coverage and an output schema, the description covers the falling-behaviors an agent needs: sequencing, no-playback constraint, URL ephemerality, and entry structure. Nothing required for correct invocation 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% and both parameters are documented in the schema (including provenance hints like 'from list_workflows'). The description adds no per-parameter meaning beyond what the schema already provides, 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+resource ('List the audio a run produced') with scope detail ('one entry per output node'). It clearly distinguishes itself from siblings like get_run_status (status vs. outputs) and download_run (listing vs. downloading).

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 precondition tied to a named sibling ('Call once get_run_status reports completed') and adds a workflow guard rail ('ask the user before you play anything'). This tells the agent both when to call and what not to assume.

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