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

Adds substantial context beyond the annotations: it clarifies that the tool replaces the study's current questions but nothing fields until publish (softening the destructiveHint), discloses that generation consumes inference credit, and warns of a possible `needs_confirmation` response. These are exactly the behavioral traits annotations cannot express.

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 paragraph that front-loads purpose, then mechanism, then prerequisites, then cost/return caveats. Every clause earns its place, though the em-dash appositives make it heavier than necessary.

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 mutation tool with no output schema, the description covers the replacement semantics, the credit cost, the precondition, and the confirmation state. The main remaining gap is the undocumented approvalId parameter, which an agent may need in the needs_confirmation flow.

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 only 25% schema coverage across 4 parameters, the description must carry more of the load. It explains `steer` well with a worked example ('focus on pricing'), but says nothing about `approvalId` (only obliquely hinted by `needs_confirmation`) and nothing about `studyId` beyond implicitness.

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 ('drafts a survey') and immediately narrows it with 'GROUNDED in the study's completed interviews', which distinguishes it from the generic prism_studies_draft and prism_studies_draft_standalone siblings. The mechanism (recurring claims become questions, tensions become choices) tells an agent exactly what output to expect.

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?

Gives a concrete precondition ('needs at least one completed interview') and routes the agent to prism_interviews_list to check it. It does not explicitly contrast against prism_studies_draft or prism_studies_draft_standalone, so the when-to-prefer-this-over-siblings decision is left to inference.

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