production.character_adjust_shape

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

With annotations already declaring non-destructive, non-idempotent, closed-world behavior, the description adds substantive context: what is preserved (topology, weights, UVs, materials, normals), what fails (locked movement beyond tolerance, unsafe shape keys), and that edits are reversible via revert. It lacks detail on where proposals are stored or how long references remain valid.

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 purpose followed by two dense sentences; nearly every clause carries information. The mid-sentence brace of operation types is hard to parse but does not waste words.

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 five-parameter multi-mode tool with an output schema, the description supplies enough to sequence a correct call: propose, then act on the reference, with tolerance and preservation contracts stated. Missing explicit mode enumeration and the meaning of object_name leaves a small but real gap.

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 0%, so the description carries the burden. It usefully enumerates the options payload (regions_manifest, shape_keys, tolerance_m) and the full operation type list with its sub-fields, but it never explains mode values, object_name, or operation_id explicitly ('proposal reference' only hints at it), and it blurs the top-level `operation` string with the nested operation object.

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: 'Topology-preserving shape edit on a candidate mesh', plus the lifecycle (analyze/propose/preview/apply/verify/revert). It doesn't distinguish itself from nearby siblings such as character_create_candidate or mesh_candidate_create, but the purpose itself is unambiguous.

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?

The description conveys an implicit workflow: analyze/propose first, then preview/apply/verify/revert using the returned proposal reference. It never states when to choose this over sibling candidate-creation or region-definition tools, and gives no exclusions beyond the failure list.

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