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

With no annotations, the description must carry the behavioral load; it usefully discloses the subscription prerequisite, that the project cap is evaluated before the per-operator budget, and that denied events consume no budget. It still omits the outcome contract — whether a denial surfaces as an error, a flag, or a payload — for a tool that clearly performs a governed write.

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?

Dense and front-loaded: the core action and its parameters come first, then preconditions and budget semantics. Every clause carries information; only the ordering-detail sentence is slightly compressed to the point of ambiguity.

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 annotations, no output schema, and 0% schema coverage, the description covers preconditions and cap ordering but not success/denial response shape or units accounting. Adequate to invoke, incomplete for a quota-enforcing 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 coverage is 0%, so the description must compensate, and it partially does by giving the allowed surface values (merge|checkout|ci_minutes|submission) which the schema leaves as a bare string. It says nothing about units semantics (what the number counts per surface) or operator/project_id formats, leaving gaps on a 4-param tool.

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 a capacity event ... for an operator on a project', and enumerates the event surfaces. It does not explicitly differentiate itself from the sibling governor_log, so it is clear but not sibling-distinguishing.

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 a prerequisite ('Requires an active Meter + Verdicts subscription') and explains the cap-check ordering, which implies usage context. It never says when to use governor_record instead of governor_log or governor_stats, so the when-to-use guidance is left to inference.

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