production.character_inspect

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's value is in the extra context it does add: the report runs on the *undeformed* base mesh, so evaluated/modifier/posed state is deliberately excluded, and it states an explicit output boundary ('No per-vertex data'). That is meaningful disclosure beyond the annotations, though it says nothing about cost, mesh-size limits, or failure modes when the object is not a character mesh.

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?

A single front-loaded sentence: the primary subject ('Character mesh report on the undeformed base mesh') comes first, followed by a dense but well-ordered list of what it returns, closing with the explicit exclusion. No filler and no redundancy with the schema.

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 an output schema present, the return values need no prose explanation, and the description correctly spends its space on scope (undeformed base mesh), coverage, and exclusions. What is missing is the preconditions (the object must be a character mesh) and any hint of parameter meaning, which keeps it short of complete.

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 0%, so the description carries the full burden, and it only partially discharges it. 'Symmetry (mirror X distances)' hints that mirror_fraction is a mirror-distance tolerance, but the unit, what it is compared against, and the meaning of the 0.005 default are unexplained, and object_name is never clarified (presumably the target mesh object, but not stated).

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 concrete verb+resource (a mesh report on the undeformed base mesh) and enumerates the specific content: counts, dimensions, symmetry, topology warnings, weight coverage, rig/shape-key state, region candidates. This clearly separates it from the analyze_* siblings that report on a single dimension, but it does not name those siblings explicitly.

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?

There is no when-to-use guidance and no reference to alternatives, despite many adjacent tools (character_analyze_asymmetry, character_analyze_proportions, character_modeling_audit) that overlap with what this report returns. The only scoping statement, 'No per-vertex data,' is a limitation rather than usage direction; an agent must infer that this is the first-pass overview call.

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