production.bake_generate_cage

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

Annotations declare readOnlyHint=false and destructiveHint=false; the description reinforces this by asserting the new cage is non-destructive and the original LOW stays the game mesh — a genuinely useful side-effect guarantee. The gate terminology (penetration/miss/max-distance/intersection) hints at how acceptance is decided. It still does not describe what 'revert' restores or any prerequisite/checkpoint requirement.

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 dense sentences with zero filler, front-loaded with the mutation-and-safety fact before the configuration detail. Every clause (non-destructive, LOW topology, gate names, original preserved) carries information an agent needs.

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 need no explanation. But for a mutation tool with five undocumented, non-required parameters, the description leaves operation_id (resume/idempotency?) and relationship undefined — gaps that affect correct invocation. Adequate but with real holes.

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% and no enums are declared, so all five parameters (mode, operation, operation_id, relationship, options) are opaque from structure alone. The description implies that the verb list maps to mode/operation values and that the gates live in 'options', but it never binds these clues to specific parameter names. Partial compensation, not enough.

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+resource: generating a NEW non-destructive LOW-topology cage, with the key invariant that the original LOW mesh remains the game mesh. This distinguishes it from the bake_* analysis/validate siblings (bake_prepare_pairs, bake_analyze_ray_distance, bake_validate). Slightly obscured by the dense 'Propose/preview/apply/verify/revert' prefix, but the core purpose is legible.

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 'Propose/preview/apply/verify/revert' sequence implies a workflow lifecycle and that the agent should pick the appropriate stage, but it never says which stage to use when, nor does it name a sibling to prefer for pure analysis (e.g. bake_analyze_ray_distance). Usage is implied rather than stated.

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