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

The annotations already declare the tool read-only and idempotent, so the description's additional value is its non-obvious counting semantics: only completed attempts are considered, and ALL attempts are counted rather than just the last one. It also provides an interpretation heuristic. No contradiction with the annotations.

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, purposeful sentences: the first states the core report contents, the second adds the crucial all-attempts behavior, and the third gives practical interpretation guidance. There is no filler or repetition of schema/annotation 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 low-complexity, one-parameter read-only report, the description covers the metric definitions, the attempt scope, and the meaning of low percentages. It does not specify the output format or ordering, but given no output schema and a simple integer input, the description is sufficiently complete for an agent to invoke the tool correctly.

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?

The sole parameter test_id has no schema description, and the description only indirectly refers to 'the test' without explicitly stating that test_id selects which test's questions to analyze. This is a gap at 0% schema coverage, but the single integer parameter is simple and the description does provide some semantic link by framing the tool around a specific test.

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 specifies exactly what the tool computes: for each test question, the number of answers and the share of correct answers across completed attempts. It also adds the distinctive all-attempts-vs-last-attempt nuance, which differentiates it from other analytics tools, though it does not explicitly name a sibling.

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?

The description gives clear usage context: it is meant to reveal questions where people stumble, and it explains why counting all attempts is necessary ('a question stumbled on from the first time is visible only this way'). It offers an actionable interpretation threshold (<50% correct means the question should be reviewed), but it does not explicitly name alternatives or say 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.