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

Goes well beyond the annotations by disclosing per-model credit costs (5/10/20/40 for texturing, 50 for remesh) and the async pattern: waits ~45 s then returns job_id for get_job. That is exactly the kind of cost and latency context annotations cannot express. It stops short of explaining failure behavior, what max_credits does when exceeded, or how wait_seconds interacts with the stated 45 s wait.

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?

The core scope is front-loaded in the first clause, and the credit table and chaining note follow in priority order. The parenthetical credit lists are dense but each parenthetical carries real information; no sentence is pure 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?

For an async, open-world generation tool with an output schema, it covers cost, input forms, wait duration and the follow-up call, which is most of what an agent needs. The remaining gap is the mesh-vs-model parameter ambiguity in a 9-parameter, nested-object schema.

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?

With 56% schema coverage the description must compensate, and it partially does by clarifying that mesh accepts a URL, upload_file id, library id or job id, reinforcing chaining. However it never resolves the confusing overlap between 'mesh' and 'model' (both described as the model), and leaves max_credits and idempotency_key entirely unaddressed in the 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?

States a specific verb and resource ('Change a model you have') and immediately enumerates the two operations, retexture and remesh, with the concrete models that back each. This makes it distinguishable at a glance from generate_model and generate_texture, which create rather than modify.

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?

Explicitly scopes usage to models you already have and names an exclusion: 'To reduce, compress, convert or repair a file, use gltf-transform or Blender locally.' It also states the input forms so steps chain without downloading, and points to get_job for the result.

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