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

Annotations declare destructive=true, but the description goes well beyond: it documents the two-step confirmation handshake (first call returns a preview without deleting, second call requires the exact confirmation string), declares irreversibility, lists the status outcomes (needs_confirmation / deleted / not_found) and states that retrying after not_found is safe. This is exactly the extra behavioral context annotations cannot carry.

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?

Purpose and safety gate are front-loaded, and each line carries actionable information (when not to call, what survives, the confirmation flow, status meanings). Slight redundancy between ほかの案件・会社情報…は残る and 削除後も同じ制度の別案件は残る repeats the same assurance twice.

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 destructive two-parameter tool this covers everything an agent needs: intent gate, preview-then-confirm protocol, irreversibility warning, sibling redirect, and status outcomes (with an output schema also present). No ambiguity remains about how to call it safely.

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 0%, so the description must compensate, and it does for the critical parameter: confirmation is explained as requiring the exact literal 「この申請書類を削除する」 plus the two-phase protocol that governs when to pass it. case_id is only implied by the title and the deletion scope rather than described, which is the one remaining gap.

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 (削除する) and resource (申請案件1件), and enumerates exactly what is removed: 記入内容・様式・記入済みファイル・ダウンロードURL. It also delimits scope against siblings by noting that ほかの案件・会社情報・ウォッチリスト・接続設定 remain.

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?

Gives an explicit inclusion criterion (利用者がこの案件の削除を明示的に求めたときだけ), an explicit exclusion (曖昧な「やり直して」では使わない), and a named alternative for the adjacent intent (start_application(new_draft=true)). Nothing 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.