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

Annotations declare readOnlyHint=false and destructiveHint=false; the description adds substantive context beyond that: hard limits (1–40 items, ≤2 sheets, ≤24 questions per sheet) and an explicit failure contract where nothing is generated and all targets plus inspection results are returned. It also clarifies a scope boundary — saving and PDF conversion happen at the link destination, not here.

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 compact sentences, front-loaded with the operation and its output shape, then the failure branch, then the out-of-scope note. Dense but every sentence carries distinct information; no filler.

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?

With no output schema, the description does the work of describing both return shapes (draft + question/answer confirmation links, or inspection results + all targets) and the size limits that determine success. Adequate for an agent to call it correctly and interpret the result.

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 coverage is 100% and the single 'manuscript' parameter's expected contents (target list, question text, answers, provenance, schemaVersion=1) are already documented in the schema. The description only adds the 1–40 item count constraint, so it is a modest supplement rather than a semantic gain — 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 pair: inspecting a 1–40 item manuscript and producing a draft kanji worksheet (up to 2 A4 sheets, ≤24 questions each). The '原稿から' (from a manuscript) framing implicitly separates it from create_kanji_worksheet and create_kanji_worksheet_from_words, but those siblings are never named.

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 makes clear this is the path when you already have a completed manuscript with answers and review targets, and it explains the defect branch (no draft is produced; inspection results are returned). It never states when to prefer create_kanji_worksheet or create_kanji_worksheet_from_words instead, so the routing decision 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.