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

With no annotations, the description carries the full burden, and it does add real behavioral color: the output carries observed_at, uncertainty and limits fields, and can return an INSUFFICIENT_EVIDENCE state that is not a ranking. It still omits read-only/permission expectations, error behavior, and return shape, so it is only partially transparent.

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?

Two short sentences with no padding, and the resource statement is front-loaded ahead of the citation advice. However, the brevity comes at the cost of obscurity rather than efficiency — the second sentence mixes usage rules with output interpretation in a dense fragment.

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 and no annotations, so the description's mention of observed_at, uncertainty, limits, and INSUFFICIENT_EVIDENCE is genuinely needed and partially fills the gap. Missing are the overall return structure, category discovery, and any relation to sibling tools, leaving the definition only minimally complete for a 1-param retrieval tool.

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 description coverage is 0%, so the description must compensate for the required "category" parameter, and it does not explain valid category values, the slug format, or how to discover them (e.g., via list_categories). It only implicitly ties the input to "a category," which is already evident from the parameter name.

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?

"Canonical evidence for a category" names a resource and its scope (a category), so the agent knows it retrieves evidence-like output rather than, say, submitting a need. But the phrasing is cryptic jargon — it never says these are results/rankings/scores — and it draws no boundary against siblings such as get_run or explain_limits.

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?

The only directive is about how to cite the output ("Cite observed_at, uncertainty and limits; never the best tool"), not when to call this tool versus the alternatives. There is no when-to-use, no precondition, and no named alternative among the seven siblings.

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