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

Annotations only declare the safety/idempotency profile; the description adds the material behavior an agent needs: per-model credit prices, refusal via max_credits, a ~45 s wait that returns job_id for get_job, same-arguments resumption with no double charge, and the GLB orientation at the origin. That goes well beyond what readOnlyHint/idempotentHint convey.

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 purpose and scope, then costs, then sizing guidance, then job behavior — a sensible order. It is dense and semicolon-heavy, and the inline price list adds bulk, but nearly every clause carries information an agent would otherwise have to guess.

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 10-parameter generative tool with an output schema, the description covers cost, latency, resumption, sizing, and orientation. Gaps are small: no statement about what happens if both image and prompt are supplied, and no mention of behavior when credits are exhausted or max_credits rejects the job.

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 80%, so the baseline is 3; the description earns above that by attaching prices to model names, explaining max_credits as a spend guard, and clarifying idempotency_key's exact purpose (a second, different job). It still doesn't explain seed or wait_seconds semantics beyond the schema.

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 ("make one 3D object ... as a textured GLB") and scopes it explicitly ("never a scene") with the two input modes named. This separates it cleanly from generate_texture, edit_model, and search_assets 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 clear conditional guidance: image for pictures, prompt for descriptions, max_faces and style=lowpoly for game/web low-poly kits, max_credits to cap spend, new idempotency_key only to force a second job. What's missing is explicit routing to siblings (e.g. edit_model for changing an existing model, generate_texture for textures only) and whether image and prompt can be combined.

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