get_run_assets

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

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses two traits — links expire ('temporary') and the call is free ('spends no credits') — but omits link lifetime, whether links are publicly accessible without auth, whether all outputs are covered, and whether repeated calls regenerate links.

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?

Two short sentences, front-loaded with what the tool returns and followed by the cost caveat; nothing is wasted. The telegraphic fragments are efficient rather than padded.

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 one-parameter read tool with no output schema, the core is covered: it returns links and costs nothing. Missing expiry behavior, response shape (list vs map of links), and whether the links point to all outputs or a subset keep it at minimum-viable rather than complete.

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 0% for the single run_id parameter, so the description must compensate. 'A run's outputs' does implicitly convey that run_id selects which run's artifacts are returned, but it adds no format, source, or validity guidance for the identifier.

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?

Names a concrete resource — temporary download links for a run's outputs — which is clearly distinct from siblings like get_run (run metadata) and quote_video/plan_edit (analysis and editing). It is a noun phrase rather than a verb phrase, so the agent must infer the action is 'fetch/return links', but the scope of the resource is unambiguous.

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?

'Spends no credits' is a useful selection cue implying this should be preferred over billed retrieval paths, and 'temporary' hints at when the result is appropriate. However, it never states when to call this instead of get_run, nor whether it should be called before or after other run operations.

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