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

No annotations are provided, so the description carries the burden, but 'stats' plus the named metrics reasonably communicate a read-only aggregation, which is the main behavioral fact an agent needs. It adds no detail on failure modes (unknown project_id), cost/latency on large projects, or what 'surface' means in the breakdown.

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?

One front-loaded sentence with no filler; the scope and output metrics come first. Only minor cost is unexplained domain jargon (HHI, 'surface'), which isn't padding but does reduce first-read clarity.

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 one parameter, no output schema, and no annotations, the description does cover what comes back by enumerating the metrics, which is the biggest gap it could have filled. It still leaves 'surface' undefined and says nothing about result shape or behavior when the project is unknown, so it is adequate rather than complete.

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% for the single parameter, so the description must compensate. Saying the stats are 'for a project' does link implicitly to project_id, and the parameter name is self-describing, but nothing clarifies what identifier format is expected (slug vs numeric ID) or which project scope is applied.

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 names a concrete resource ('a project') and concrete outputs ('top-operator share, HHI per surface and overall'), so an agent knows this returns concentration metrics rather than raw records. It never states an explicit verb ('returns', 'computes') and doesn't distinguish itself from siblings like governor_log or governor_record, but the metric-level specificity offsets that.

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?

There is no guidance on when to use this versus governor_log/governor_record or verdict_queue, no prerequisites (does the project need to exist, does the caller need a role?), and no statement of what it is not for. The agent must infer everything from the name and the metric list.

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