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

Annotations already declare readOnly=true, idempotent=true, closed-world, and non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a hard cap of 20 results and the fact that each result includes question text and answer.

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 tight sentences with no filler. The core capability (returns up to 20 character questions with text and answers) is front-loaded before the use-case sentence.

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, but the description discloses the essential return shape (question text + answer, max 20) and the annotations carry the safety profile. Combined with 100% schema coverage, an agent has what it needs to call this correctly, though richer detail on result ordering or filtering interaction would help.

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 all four parameters (char, type, grade, learningScope) are already documented in the schema. The description only mentions the target character and does not add filtering semantics beyond what the schema provides; baseline 3 applies.

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: it returns existing questions for a given character, capped at 20, with question text and answers. It also frames the result as candidates for replacing one worksheet question, which differentiates it from replace_question (the action) and create_kanji_worksheet.

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 clause 'プリント案の1問を差し替える候補になります' gives clear usage context (finding candidates before a swap), but it never names a sibling alternative or states when-not to use it. Usage is implied rather than explicit.

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