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

Annotations already declare readOnlyHint=true, destructiveHint=false and closed-world, so the safety profile is covered. The description adds genuine behavioral value beyond that: it asserts the numbers are pre-computed and trustworthy ('without counting raw rows'), which is the key trait an agent needs in order to avoid redundant manual aggregation, and it discloses the quality-flag content (speeders, duplicate ids) that callers should expect.

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 directive sentence is well front-loaded and the closing 'ALWAYS...never...' instruction is the right note to end on. But the middle is a single sprawling sentence with three levels of nested parentheses enumerating every aggregate type, which is harder to scan than a short bulleted structure would be.

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 full burden of describing return values, and it does so comprehensively — funnel stages, per-question aggregate types, and quality flags. Combined with annotations covering safety, an agent has everything needed to decide to call this tool and interpret the payload.

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 only 50%: the workspace parameter is documented in the schema, but studyId carries no description anywhere. The tool description says nothing at all about either parameter — no format for studyId, no guidance on when the workspace slug is required. With low coverage, the description was expected to compensate and does not.

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 names a concrete resource (a study's computed results) and enumerates exactly what those results contain — funnel metrics, per-question aggregates, quality flags — so an agent knows precisely what this tool returns. It does not, however, differentiate itself from near-neighbors such as prism_studies_analyze, prism_studies_cut, or prism_studies_report, which an agent could easily confuse it with.

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 gives an explicit directive — 'ALWAYS use this for quantitative questions about a study — never tally answers yourself' — which tells the agent both when to use it and what not to substitute for it. It stops short of naming the sibling tools (report, analyze, cut) that would cover other question types, leaving that inference to the caller.

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