audit_collision_profiles

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

The description frames this as a benign, cheap in-memory read of collision settings with no asset loading, yet the annotations declare destructiveHint: true and readOnlyHint: false. Nothing in the description accounts for a destructive write, so the safety profile the agent reads from the annotations conflicts with the operation the description portrays.

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?

Purpose is front-loaded, followed by the cheapness/cost note, the contrast with sibling audits, then the return shape and next step. Dense but every clause carries information; only the informal "Cheap:" framing is mildly loose.

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?

No output schema exists, and the description compensates by naming the return shape ({ path, summary: {...} }) and the follow-up tool (read_mcp_audit_file). With zero parameters, cost characteristics, and return contract all covered, the definition is nearly complete; the unexplained destructive annotation is the one loose thread.

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?

The tool takes zero parameters, so the baseline is 4. The description reinforces this by noting it takes no folder_path and no max_results, which is the useful information available about its (empty) parameter surface.

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 concrete verb and resource — an aggregate report of every collision profile and every collision channel (built-in + custom), including which ECC_GameTraceChannelN slots are taken. It explicitly differentiates itself from the other audit_* sweeps and from add_collision_channel, so the agent can select it without opening schemas.

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?

Gives an explicit when-to-use ("the question to ask before add_collision_channel") and an explicit contrast with alternatives ("unlike the other audit_* sweeps it takes no folder_path and no max_results"). Both the trigger condition and the disambiguation from siblings are stated.

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