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

Annotations already disclose readOnly=false, idempotent=false, and destructive=false; the description adds the pipeline behavior (mesh generation → auto-rigging → ready to animate), the GLB output, and the inline interactive viewer. It does not cover async/job semantics, but with annotations present this is reasonable additional context.

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 with no filler. The core action is front-loaded, and the subsequent sentences add essential scope and behavior without redundancy.

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?

Given three optional parameters, no output schema, and annotations that do not fully describe return semantics, the description could be stronger on what exactly is returned (e.g., GLB URL, job ID, or inline render). It states 'Renders inline in an interactive 3D viewer,' but an agent may still need return-contract details for downstream use.

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 100%, so the baseline is 3. The description lightly reinforces the prompt-vs-image input relationship but does not add extra semantics for allow_non_humanoid or details 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 (generate), resource (rigged, animation-ready 3D avatar), output format (GLB), and input scope (text prompt or reference image). The phrase 'Best for characters; objects are steered to the mesh generator' distinguishes it from sibling tools like mesh_forge and text_to_avatar.

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 explains when to use it ('Best for characters'), when not to ('objects are steered to the mesh generator'), and names an alternative. It also signals it is a one-step tool, which orients the agent toward selecting this over chaining separate mesh-generation and rigging steps.

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