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

Annotations declare a non-readonly, non-idempotent, non-destructive mutation, and the description adds real context beyond them: it renders the existing takes unchanged, avoids creating an extra shoot, and warns that it returns rendering status only and never claims completion. This is strong disclosure, though it does not state why the operation is non-idempotent (e.g. repeated retries) or how long rendering takes.

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?

Four short sentences, each doing distinct work: purpose, timing, return semantics, and the alternative tool. The critical constraint (no new shoot, no script change) is front-loaded and no sentence is filler.

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 the description usefully covers the return behavior ('rendering status, never claims completion'), and it fully covers routing and constraints. It falls short only on the four unexplained optional parameters, which matters for a five-parameter tool.

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% across five parameters, so the description must carry the burden and largely does not. It clarifies only that shootId refers to an existing shoot; music, renderCta, renderHook, and renderCaptions are undocumented in both schema and description, leaving the agent to guess their meaning and defaults.

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 pair (render/retry) and a precise resource (the exact existing phone shoot using all saved takes in order), and explicitly excludes script changes or creating another shoot. An agent can separate this from create_video_shoot and get_video_shoot_status 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 explicit timing ('Use after the user asks to finish/retry their video') and an explicit alternative with its condition ('For re-filming use create_video_shoot.sourceShootId instead'). Both the when and the when-not are named, not inferred.

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