record_edit_outcome

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It conveys the tool's semantic role as a feedback signal but says nothing about persistence, idempotency (what happens on duplicate request_id), required permissions, or error behavior for an unrecognized outcome — significant gaps for a state-recording mutation.

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?

Front-loaded with the action, then the rationale, then an Args list — no filler or repetition. The 'STRONG signal' line is slightly editorial but earns its place by motivating why the call matters; overall tight and well organized.

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?

The presence of an output schema removes the need to describe return values, and the parameters are adequately covered. What is missing is any tie-in to the surrounding workflow (recording happens after an edit lands) and differentiation from the other record_* siblings, which an agent choosing among ~70 tools would need.

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%, so the description must compensate and largely does: request_id is anchored to the optimize_context response field, outcome gets the three valid literals ('accepted'/'reverted'/'retried') that the schema itself omits as an enum, and files_modified is explained as 'number of files touched by the edit'. Only the files_modified default/optionality is left implicit.

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 gives a specific verb+resource ('Record whether the user accepted, reverted, or retried an AI edit') and even enumerates the discrete outcome values. It is clear on its own, but it never distinguishes itself from the many sibling record_* tools (record_outcome, record_test_result, record_ci_result, record_command_exit), so an agent must infer the boundary.

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 'STRONG signal' sentence implies the context (this is called after the user responds to a generated edit) and the request_id arg ties it to the optimize_context flow. However it never states explicitly when to call this versus record_outcome or record_test_result, and gives no exclusions or prerequisites.

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