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

Even though annotations already indicate read-only, idempotent, and non-destructive behavior, the description adds valuable context: 'no pagination — max 250 questions', 'IsLocked true means the survey has responses and its questions can no longer be replaced', and a display rule ('never show SurveyToken/QuestionToken UUIDs; the PublicLink IS shareable'). This goes beyond the annotations and enriches the agent's understanding of constraints and side effects.

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 description is verbose and redundant. The initial paragraph is followed by a '## When to use' section that repeats almost verbatim the same content, and a '## Parameters to validate before calling' section that duplicates the schema. While structured with headers, the repetition makes it less concise and wastes tokens for the agent.

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?

Given no output schema and a single parameter, the description covers necessary context: prerequisites, error handling, limits, the meaning of IsLocked, and display rules. It lacks a detailed description of the response structure, but the statements about question set and locked status provide a good overall picture. Slight deduction for not outlining the full return fields.

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 100% — the only parameter survey_token is fully described in the schema: 'The survey token (UUID v4). Get it via fetch_surveys'. The description repeats this but adds no new meaning. Baseline 3 is appropriate because the schema does all the heavy lifting, and the description doesn't compensate further.

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 states a specific verb and resource: 'Fetch the full detail of a single survey, including its complete question set.' It clearly distinguishes from siblings by naming fetch_survey_report for aggregated results and fetch_survey_responses for individual responses, as well as fetch_surveys for listing surveys. The purpose is unambiguous and not a tautology.

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?

Explicit guidance is provided: 'Use fetch_surveys first to get the survey_token' sets a prerequisite, the 403 'module is not enabled' error includes an action (do NOT retry, contact support), and alternatives are named for related tasks ('For aggregated results use fetch_survey_report; for individual responses use fetch_survey_responses'). This fully addresses when and not to use the tool.

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