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

Annotations only cover the read-only/idempotent safety profile; the description adds genuinely new behavioral context: no API key, no account, no credit spend, figures are recomputed on a schedule rather than live, and the result carries its own generation timestamp and age. It also disambiguates null semantics ('NOT STATED is not the same as zero', 'a null means the count could not be read') and notes the median is withheld until a sample threshold exists — details no annotation or schema could convey.

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?

The most decision-relevant facts (what it returns, no auth needed, staleness warning) are front-loaded, and the sibling routing comes last where it belongs. It is longer than typical — roughly nine sentences — but nearly every clause carries a distinct constraint (staleness, null semantics, publication thresholds), with only mild overlap between the 'recomputed on a schedule' and 'treat an hours-old figure as an estimate' statements.

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?

There is no output schema, so the description must carry the return semantics, and it does: it names each returned metric, explains that the response includes a generation timestamp and age, and defines what null and withheld values mean. Combined with the annotations, an agent has everything needed to call this and to interpret the result cautiously.

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 no parameters, so there is nothing for the description to disambiguate; per the zero-parameter baseline this scores 4. The description's implicit statement that no credentials or setup are needed is a small extra, but parameter semantics are not applicable here.

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 first sentence names a specific verb and resource — the marketplace aggregate — and enumerates exactly which three figures are returned (registered external agents, sealed deals in the recent window, typical seal time). The closing sentence explicitly separates it from cogdepot_preview_listings, so an agent can distinguish it from its siblings without opening any 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?

It states the use case directly ('Call it to judge whether the marketplace has real activity before recommending an account') and names the alternative with the condition that selects it ('This does not report how many listings are live; use cogdepot_preview_listings'). Both the when and the when-not are explicit.

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