production.physics_plan_cloth_pins

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

Beyond the annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description adds real behavioral context: mutations are confined to isolated secondary candidates, body/face are preserved, apply safety defaults to false, and there are fixed plans with explicit QA/review gates. This meaningfully characterizes the mutation scope and safety posture that annotations alone leave ambiguous.

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?

Two compact sentences with the mode selection and safety default front-loaded; little waste. The only inefficiency is repeating the tool name as the resource, which costs a clause without adding information.

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?

A mutation-capable tool with 6 undocumented optional parameters and a large family of near-identical physics_* siblings needs far more: what each parameter does and how it differs from adjacent planners. The output schema covers returns and annotations cover safety, but the parameter and sibling ambiguity leaves the agent under-informed.

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 6 parameters at 0% schema description coverage, the description must carry the load but does not. The only parameter touched is 'apply', and the note that it defaults to false merely repeats the schema default; brief, intent, options, physics, and object_name are entirely unexplained.

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 states inspect/propose/execute on 'cloth pins' scoped to isolated secondary candidates, which is more specific than the name alone. However, the resource is essentially the tool name restated ('physics_plan_cloth_pins'), and it does not distinguish this from nearby siblings like physics_plan, physics_plan_hair, or physics_setup_cloth, leaving the agent unsure which planner to pick.

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?

Only 'apply defaults false' hints at an inspect-vs-execute usage pattern, and 'explicit QA/review gates' implies a workflow. There is no guidance on when to choose this over physics_plan, physics_plan_hair, physics_analyze_cloth, or physics_setup_cloth, despite the dense sibling set.

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