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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so the safety profile is covered. The description still adds genuinely new behavioral context: that no authentication is needed and that only currently playable assessments are included, which an agent cannot infer from the annotations or empty schema.

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 short sentence that leads with the access condition and the scope, with no filler or repetition. Every clause carries 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 zero-parameter read tool with no output schema, the description does the heavy lifting by naming what comes back (assessments, question counts, versions). It could say more about ordering or whether results are cached, but nothing essential is missing.

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 tool takes zero parameters, so per the rubric the baseline is 4 and there is no schema-level parameter documentation to duplicate or contradict. The description correctly implies no filtering input is required.

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 pair (view/list assessments) and even names the payload fields returned (题量 question count, 版本 version), which is far more than a tautology. It does not explicitly contrast itself with sibling get_assessment or the other get_* tools, so it stops short of 5.

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?

'免登录' (no login required) gives a usable condition for reaching for this tool over authenticated siblings, and '当前可玩' scopes it to currently available content. However it never says when to prefer this over get_assessment for details or get_results for data, so routing 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.