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

Adds substantial context beyond the annotations: the 30+/2+ data thresholds, that recompute overwrites existing results, that naming runs against inference credit (a cost), and that a needs_confirmation result is possible. This is exactly the behavioral disclosure the destructiveHint implies, made concrete.

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?

Three tight sentences, front-loaded with the operation and followed by preconditions and side effects. Every clause carries information; none is redundant.

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 compute tool with no output schema, the description covers the operation, prerequisites, cost, destructive overwrite, and a possible confirmation outcome well. The remaining gap is parameter meaning, particularly approvalId, against only 33% schema coverage.

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 33% and the description adds no parameter meaning at all. The required studyId and the approvalId are undocumented in both places, leaving the agent to guess how approval relates to the mentioned needs_confirmation flow. A likely approvalId connection is never made explicit.

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 and mechanism: 'Runs k-means over the study's numeric answers (silhouette-picked k) and names the discovered segments.' This clearly distinguishes the compute operation from generic study tools. It does not, however, explicitly differentiate itself from the closely named sibling prism_studies_segments, leaving the agent to infer the relationship.

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?

Provides concrete preconditions for use: 'Needs 30+ responses and 2+ numeric questions.' This is genuine when-to-use guidance that an agent can act on. It stops short of naming alternatives (e.g., prism_studies_segments or prism_studies_analyze) or stating when not to use it.

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