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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is fully covered and the description adds nothing to it. It omits aggregation-relevant behavior such as whether counts reflect the filter set, how limit/offset apply to facet values, and what the response shape looks like. The "Served by r4ck (docs link)" sentence is attribution, not behavior.

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, front-loaded with the core statement of what is returned. The second sentence is boilerplate attribution that consumes a fifth of the text without helping selection or invocation, keeping it short of a 5.

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?

For a 26-parameter aggregation tool with no output schema, the agent is left not knowing which facet dimension is returned, what the response container looks like, or whether pagination applies to counts. Given no output schema and a high parameter count, the description does far too little to be safely invocable.

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?

With 26 parameters at 58% schema coverage, the description carries a real burden here, yet it contributes no parameter meaning beyond "optional filter set". It does not clarify whether filters constrain the counts, whether sort/order/limit apply to the facet values or the underlying rows, or how q interacts with the explicit fields — all of which are ambiguous for an aggregation endpoint.

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?

"Every facet value with its count, under an optional filter set" names a specific output shape (aggregated counts per facet value) rather than a generic search, which distinguishes it in spirit from r4ck_search_servers and r4ck_cheapest. What it never states is which fields are faceted, so the agent knows the form of the answer but not its subject matter.

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 when-to-use guidance at all: nothing says to call this to discover available providers/regions/kinds before filtering, and nothing says which sibling to use when raw rows are wanted instead of counts. The phrase "under an optional filter set" implies the filters can be reused from search, but that is inference, not guidance.

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