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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds meaning beyond that: 'Free: it starts nothing' confirms no analysis is kicked off and no cost is incurred, and 'Empty if none were run' discloses the degenerate return case, which 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?

Three short clauses, front-loaded with the core action and scope, then cost/side-effect, then empty-state and the alternative. Nothing is redundant and no sentence could be removed without losing information.

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 single-parameter, read-only tool with rich annotations and a declared output schema, the description covers the essentials: what it returns, what happens when nothing exists, that it costs nothing, and where the alternative lives. Only marginal gaps remain, such as ordering or volume of returned analyses, which the output schema can carry.

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% with 'Question ID' documented, so the baseline is 3. The description goes further by giving provenance for the value ('surveyItemId from survey_get'), telling the agent where to obtain it without a discovery detour — genuine added meaning over the schema.

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 opens with a specific verb+resource pair ('Read AI analyses already run') and scopes it to one question, naming the exact parameter that identifies the question. It is immediately distinguishable from siblings like report_get or responses_read, and 'analysis history' vs 'answers' is a clear conceptual split.

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 states the positive case (read analyses already run), a negative/empty case ('Empty if none were run'), and routes the agent to an alternative ('to analyze answers yourself, read them with responses_read'). It also notes the call is free so the agent needn't worry about triggering work. It stops short of comparing against the other report_* siblings, but the key routing decision is explicit.

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