suggest_retarget_profile_map

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

No annotations are provided, so the description carries the burden. It discloses an important behavioral trait: 'output always requires human review', which implies the tool doesn't commit changes and returns suggestions only. However, it does not describe what happens on failure, whether the output is a full map or just candidate matches, or what the output schema contains (though an output schema exists). The description adds the human-review requirement, which is valuable, but it's minimal.

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 description is extremely concise: one sentence with two clauses. It front-loads the core purpose and adds one behavioral note. No waste, but it is so short it lacks detail for other dimensions. For what it intends to cover, it's well-structured.

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?

The tool takes a complex scene_snapshot object, has an output schema, and is in a domain where sibling tools suggest a workflow (validate/analyze/suggest). The description is insufficient: it does not mention how the scene_snapshot is used, whether action_name is required for generating a map, what the output format is (despite an output schema), or potential side effects. Given the complexity of the input and the tool's role in a pipeline, the description is too thin.

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%, meaning the description provides no parameter explanations beyond what the schema names suggest. The schema itself has 5 parameters (source_rig_id, target_rig_id, profile_name, scene_snapshot, action_name optional) with clear names and types, but no descriptions anywhere. The tool description does not explain the role of scene_snapshot or action_name, nor how they affect the suggestion. Since coverage is 0%, the description must compensate, and it fails to do so.

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?

The description clearly states the tool's purpose: 'Suggest exact/normalized/alias bone matches' for retarget profiles. It identifies the specific action (suggest bone matches) and the resource (retarget profile map). However, it doesn't explicitly distinguish itself from sibling tools like 'validate_retarget_profile' or 'analyze_retarget_profile', though the verb 'suggest' implies a generative step versus validation/analysis.

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 implies it's used when you need to suggest bone matches for a retarget profile, but it doesn't explicitly state when to use it versus alternatives like 'validate_retarget_profile' or 'analyze_retarget_profile'. It also doesn't mention prerequisites (e.g., that the profile must exist) or that the scene_snapshot is required. The sentence 'output always requires human review' gives some usage guidance (the output shouldn't be applied automatically), but it lacks explicit exclusions or alternative tool recommendations.

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