production.physics_bake_secondary_motion

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

Annotations already declare the safety profile (not read-only, not destructive, not idempotent). The description adds real context beyond that: default dry-run via apply=false, a 'fixed physics plan', and required QA/review gates, plus the isolation guarantee that body/face are preserved. These are meaningful but not richly detailed (no failure modes, no cache behavior).

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, front-loaded with the action and scope, with the dry-run default and gating constraints early. Minimal waste, though the phrase 'fixed physics plan' is slightly cryptic.

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?

Output schema exists so return values needn't be explained, but with 7 parameters at 0% coverage and a non-trivial, partly-mutating tool, the description leaves major gaps about what each input controls (intent, physics, options, operation_id). The gating/isolation notes help but don't cover parameter meaning.

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% across 7 parameters, so the description must carry the burden. It only clarifies one parameter ('apply defaults false'); briefing, intent, options, physics, object_name, and operation_id are left completely unexplained in both schema and description.

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 the verb 'inspect, propose, or execute' and the resource 'physics_bake_secondary_motion on isolated secondary candidates', plus a scope note (body/face preserved). But the resource is essentially the tool name restated, and it doesn't distinguish itself from nearby siblings like physics_bake_cache or physics_generate_secondary_bones.

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?

'apply defaults false' and 'explicit QA/review gates' imply a dry-run-first workflow and gated execution, which is useful implied guidance. However, there's no explicit statement of when to use this versus the many sibling bake/generate tools, so the agent must infer routing.

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