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

No annotations are present, so the description must disclose behavior itself. It does so by stating the result always includes a `coverage` block and warns that enrichment depth (catalog_gap) affects the numbers, so part of any cohort number reflects coverage, not just market reality. It also flags 'computed live,' which is a useful behavioral detail. This is strong context beyond the schema.

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 description is fairly dense, packing many metrics into one long sentence, and starts with the stylized 'INFLUENCE —' which adds no information. The coverage caveat is valuable but placed in a long final sentence. It is not bloated, but it could be better structured and front-loaded.

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 and no annotations, the description takes on the burden of explaining returns, and it does cover the key metrics and the coverage block. It also gives the critical interpretation caveat about enrichment depth. However, it leaves parameter semantics and explicit usage guidance to inference, so it is not fully 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?

Of the three parameters, only `context` has a schema description (33% coverage), leaving `kind` and `slug` unexplained in the schema. The description does not compensate: it never explains how kind/slug select the cohort. The `kind` enum helps, but `slug` is opaque, and the description doesn't clarify it.

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?

Description names the operation (compute distribution stats for a market cohort) and lists specific outputs (mean/median/min/max/stdev, agent-readiness spread, band split, per-facet averages, artifact adoption rates). It frames the tool as the 'market-stats sheet' from a Trend Report, distinguishing it from siblings like cohort_rankings and cohort_scores. The resource is clear enough via kind/slug parameters.

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 says 'for a whole market' and 'market-stats sheet from a Trend Report, computed live,' implying use for aggregate cohort statistics rather than individual scores. However, it never explicitly names alternatives or states when not to use this tool. The guidance is implied, not explicit, so it gets a middle score.

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