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

Annotations only tell us it is a non-idempotent, non-destructive write. The description adds substantive behavior: it increments anonymous public counters, stores no personal data, and details what Stackcut retains versus discards. This is real disclosure beyond structured fields, though the long privacy paragraph is partly general policy rather than tool-specific 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?

The precondition and core action are front-loaded well. However, the middle block is a dense data-retention policy paragraph whose sentences (tool result summarization, exit-tool logging details) drift away from what this specific tool does.

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?

With no output schema and 0% parameter coverage, the description should cover inputs and return effects more fully. It handles when-to-call and privacy well, but never clarifies what recipe_id/path_id refer to or what a successful report yields, leaving gaps for a 3-required-parameter write tool.

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% for three required parameters, so the description must carry the load. It does map the outcome enum values ('picked, switched to or reverted from'), but recipe_id and path_id are never explained, leaving two of three required arguments semantically opaque.

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 (record) plus the exact outcomes recorded ('picked, switched to or reverted from a replacement path'), so the agent knows this reports a user's path decision. It does not, however, distinguish itself from the sibling report_action_outcome and report_exit_outcome tools, leaving the boundary to inference.

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 after the user confirms what they did' gives a clear precondition, and the later mention of 'exit tools' implies a scope boundary. But it never names the alternatives (report_action_outcome, report_exit_outcome) or states when this one is preferred over them, so the routing decision is only partly supported.

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