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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well past them: no storage, no rendering, no charge; a documented inline size limit; and how non-physical models are labelled in the output. It also discloses that it wraps POST /api/v2/video-studio/templates/teardown/plan, which is unusually candid for a read-only-hinted tool.

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-loaded with the read-only tag and the core action, then the default plan contents, then the alternate mode and cost/side-effect guarantees. Dense but nearly every clause carries information. The parenthetical splice for the '3D render' labelling slightly interrupts the flow, keeping it from a 5.

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 9 parameters, nested objects, no output schema, and no required fields, the definition covers the return shape (parts list, default plan at 16:9 and 9:16, frame/worker-time estimate), the cost model, and side-effect guarantees. The main residual gap is the absence of any output schema, so the exact structure of the returned plan is only summarized rather than specified.

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 already 89%, but the description still adds meaning: the accepted model encodings and the 3 MB inline cap, the `names` map example ({ p0: "Lid" }), and the semantic consequence of `status` (anything but physical gets a '3D render' label in the film). That is genuine value beyond the schema, though `brandName`, `accent`, and `engraving` get only the schema's own text.

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?

The description gives a specific verb and resource — send a 3D model and receive its parts list, a default teardown/1 plan, and a render estimate — plus the alternate entry point (send an edited `plan` to validate and re-estimate). An agent knows exactly what this produces. It never names the closest sibling (render_motion_ad) to draw an explicit boundary, so it stops just short of a 5.

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?

Clear usage conditions: send `model` for a fresh plan, or send `plan` instead to check an edited plan against limits and re-estimate, with the two being mutually exclusive inputs. It also sets expectations ('free', 'nothing stored, rendered or charged'). It gives no explicit when-not or sibling comparison, so it is clear context rather than full routing guidance.

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