Get the shots of a run

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

Annotations already cover read-only/no-destruction, yet the description adds substantial behavioral context beyond them: preview_url is a large, expiring signed link that must not be stored, withheld fields are nulled, planned=false is a normal outcome, media_available_until limits storage, and paid_edits.enabled gates edit-based video creation. This is the kind of disclosure that changes how an agent behaves.

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?

Purpose and required input are front-loaded, and with no output schema the detailed field rundown earns its space. It is delivered as one dense unbroken block of prose, which makes the later return-shape details harder to scan than they need to be.

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?

Because there is no output schema, the description must explain the return payload, and it does so thoroughly: frame size/rate, narration timing, per-shot fields, preview_url semantics, withheld, editable.state/reason, media_available_until, and paid_edits.enabled. An agent has everything needed to interpret both success and empty states.

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 0% for the single parameter, so the description carries the burden, but it only says 'Pass the run_id' without format or provenance detail (the run_ prefix pattern lives only in the schema). Minimal compensation for the coverage gap, hence the baseline 3.

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?

Opens with a specific verb+resource ('Read the shots of a video') and names the exact producer tools (make_faceless, make_ugc) plus the required input. This distinguishes it cleanly from the sibling get_run, which returns run-level data rather than shots.

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 clear context: call it after make_faceless/make_ugc, pass the run_id, and expect planned=false as a legitimate no-shots answer rather than an error. It does not explicitly contrast the choice against the sibling get_run, so the boundary between run-level and shot-level retrieval is only implied.

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