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

Annotations declare readOnlyHint=true, so safety is covered. The description adds non-obvious behavior beyond that: the 90-day trim, that the count excludes leavers, and the counterintuitive fact that historical points can exceed the current count. It doesn't cover return shape, but that is a read-only stats tool.

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: definition, default scope, and the anomaly caveat. Front-loaded with the core metric and no filler.

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, the description must convey what comes back, and it does: two breakdowns plus a 90-day timeline, and it flags the dip anomaly. The only gap is that no formal return shape is given, which is minor for a descriptive stats endpoint.

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 100%, so the baseline is 3. The description still adds meaning by stating the effect of omitted `venue` (org-wide) and the semantic distinction between 'currently joined' and 'have not left', which goes beyond the schema's id-reference descriptions.

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 precisely what is counted ('members currently joined... who joined and have not left'), how it is split (by venue, by membership card), and what else is returned (cumulative 90-day timeline). No sibling tool offers member counts, so it is clearly distinguishable.

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?

Explains default scope ('covers every venue unless venue is given') and the quirky semantics exploration ('timeline can dip when members leave, so a past point can exceed the current count'). It does not route to an alternative tool, but for a standalone stats tool no obvious alternative exists.

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