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

Adds substantial behavior beyond the annotations: it is asynchronous, requires polling a specific sibling field until cleared, has a 30-per-day rate limit, is free, and does not take price input. Annotations only say non-read-only and non-destructive, so this description carries real operational detail.

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?

Front-loads the key facts (free, what it does, rate limit) in one sentence, then uses compact Args/Returns blocks. Every line carries information; no filler or repetition.

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 supplies the return shape ({ok, job_id, poll}) and the required follow-up polling loop, which is the critical piece an agent would otherwise miss. Nothing needed to invoke it correctly is absent.

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 50%, and the description compensates by explaining that project_id comes from project creation and that scene_uids is an optional subset selector capped at 40 for re-planning. It adds the intent behind scene_uids rather than just repeating maxItems, though the 'up to 40' duplicates the schema constraint.

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 ('Plan the project') and immediately defines what planning means ('split scenes and choose footage'). The phrase 'Takes no price' separates it from the estimation sibling without needing to name it.

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 operating context: it is free, capped at 30 plans a day, and runs asynchronously so the caller must poll studio_get_project until plan_job_id is empty. It also explains when to supply scene_uids (re-plan only those scenes) but does not explicitly name studio_estimate_project as the alternative when pricing is wanted.

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