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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered. The description still adds real behavioral value: it discloses the null return state and the shape of what is returned (segment mean vs overall), which is not in 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?

A single dense sentence with the coverage constraint front-loaded and the null behavior plus alternative named at the end. No filler.

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?

Although there is no output schema, the description compensates by describing the return structure and the null case, and it explains how segments come to exist. Complete enough for a read tool, with only the parameter gap remaining.

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 coverage is only 50%, and the description mentions neither studyId nor workspace. The undocumented studyId parameter gets no compensating explanation, so an agent gains nothing about parameters from the description beyond the schema's own workspace note.

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?

States a specific verb+resource (retrieves the stored k-means segmentation over a study's numeric answers) and details what the result contains (named segments, size, share, distinguishing features). It is clearly distinguishable from the compute sibling, which it explicitly names.

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 explains the null-when-not-computed condition and routes the agent to prism_studies_segments_compute with its prerequisites (30+ responses, 2+ numeric questions). What is missing is explicit guidance on when an agent should read segments at all versus other study outputs like results or report.

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