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

Goes beyond the annotations by stating the side-effect boundary (status and credits are untouched) and the auth requirement ('Needs the user's personal access token'). Since annotations already declare idempotentHint=true and destructiveHint=false, the description's contribution is supplementary rather than load-bearing, but it is real and useful.

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?

Three tight sentences, front-loaded with the action and its value set before the guardrail and the side-effect disclaimer. No sentence is filler; even the auth note earns its place.

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 an output schema present, return values need no explanation, and the description covers intent, guardrail, side effects and auth. The only minor gap is that the dependency on list_auto_apply_history for the id lives solely in the schema rather than the description.

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 only 50% — the outcome enum has no schema description — so the description carries the burden and does so by listing every enum value and explaining the non-obvious 'none to clear it' as a reset. It leaves the id parameter to the schema, which already documents its source, so this is close to complete.

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 and resource ('Record what the user says happened with an application that went out') and enumerates the full outcome vocabulary, including the special 'none to clear it' case. An agent can distinguish this from list_auto_apply_history or queue_for_auto_apply without opening a schema.

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 gating condition — 'Only when the user tells you; never guess' — which is exactly the when/when-not guidance an agent needs for a user-reported fact. It also bounds the scope of the write ('It changes nothing else'), so the agent knows no adjacent state is affected.

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