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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond that: what each returned question contains (misconception explanation, how to respond in class, correct method, graded practice) and that it is directly projectable. It does not mention the default/max limit behavior, which is left to the schema, keeping it below 5.

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 front-loaded purpose is good, but the parenthetical enumeration of 13 subjects is long and low-value, and the trailing English sentence ('Whole-class diagnostic questions with misconception-tagged wrong answers, every subject') duplicates what the Chinese text already said. The mixed-language restatement costs space without adding 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?

There is no output schema, so the description carries the burden of explaining returns, and it does so well by describing the question payload (misconception tagging, corrective approach, three-tier practice). Limits/pagination are omitted but are covered by the schema. Complete enough for an agent to invoke correctly without surprises.

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 description coverage is 100%, so the schema already documents code, grade, limit, topic and subject. The description's '按学科、课标要点或标准编码、年级、或关键词查' essentially restates those handles without adding syntax, format, or interaction rules beyond the schema. Baseline 3 is appropriate.

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+resource: retrieve classroom diagnostic questions, and it richly characterizes what those are (whole-class gesture answers, each wrong answer tagged with a misconception, correct approach, three-tier practice, projector-ready). An agent can distinguish this from sibling tools like get_standard or list_standards because the resource is a ready-to-use question bank rather than standards metadata. It stops short of explicitly naming any sibling, so a 4 rather than a 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?

It tells the agent which handles can be used to query (subject, standard code, grade, keyword), which implies how to call it, but gives no explicit when-to-use-vs-alternatives guidance and no exclusions. Nothing tells the agent when to prefer get_standard or search_standards instead, so usage is only implied.

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