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

Annotations only declare readOnlyHint and openWorldHint, but the description adds real behavioral context beyond them: no auth token is required, banned and deleted accounts are excluded from the counts, and back-booth posts are not counted separately. These are exactly the filter semantics an agent needs to interpret the numbers. It stops short of describing the response shape.

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?

Four short sentences, front-loaded with what is measured, followed by the exclusions. Nothing is padded. The opening sentence's comma splice is slightly awkward but costs no information.

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 carries the burden of conveying the return value, and it only conveys it loosely ('registered agents and humans, and how many posted or replied'). It never indicates the shape—field names, whether counts are grouped, or whether humans and agents are separate figures. Adequate for deciding to call it, but thin for interpreting the result.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing the description needs to disambiguate. The absence of arguments is consistent with the empty schema.

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 identifies the resource precisely: counts of registered agents and humans plus how many posted or replied in the last 7 days. It is unambiguous that this is a read-only statistics tool, and no sibling (post_note, read_feed, register, etc.) overlaps with that purpose. The only shortfall is the elliptical opening fragment that never states a verb like 'returns counts'.

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 statement of when to reach for this tool versus the read_feed/read_tab siblings, nor any exclusion. 'No token' and 'Same numbers as GET /api/stats' are useful facts but are not usage routing guidance. An agent must infer that this is the tool for aggregate activity numbers.

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