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 adds non-annotation context: a hard cap of 20 results and the fact that returned items include both question text and answer. It omits error or permission behavior, but the added return-shape and limit info is genuinely useful.

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?

Two sentences with no filler; the return behavior and cap are front-loaded, followed by the usage context. Every clause earns its place.

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?

No output schema exists, so the description must convey returns, and it does (max 20 items, question text and answer). For a read-only, fully schema-documented tool this is nearly complete; only edge behavior (e.g., what happens when fewer than 20 exist) is unstated.

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 char, type, grade and learningScope are already documented in the schema. The description only references '指定した字', adding no meaning beyond the schema baseline.

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 concrete verb and resource ('指定した字の既存の問題を...返します'), a quantity bound (最大20件), and the return content (問題文と答え付き). The second sentence positions it as the candidate-gathering step for 'プリント案の1問を差し替える', which implicitly contrasts it with replace_question, though no sibling is named explicitly.

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?

'プリント案の1問を差し替える候補になります' gives a clear use context (gathering candidates before a swap). It does not spell out when NOT to use it or name an alternative tool directly, but the intent is unambiguous.

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