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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the corpus boundary (loaded pages only), the 'use this first' priority, and a fallback protocol (rephrase, never guess). No contradiction with the read-only, closed-world annotations.

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 is front-loaded, then scope, then fallback guidance—a logical order. It runs fairly long, but each clause (corpus limit, don't-guess fallback) carries distinct operational value, so little is wasted.

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 an output schema present, return values needn't be explained, and the description correctly focuses on scope, priority, and not-found behavior. For a single-parameter search tool with strong annotations, this is nearly complete; only the missing differentiation from 'search_pages' holds it back.

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% and there is a single 'query' parameter, so the schema already fully documents it (including an example). The description adds no extra syntax, format, or matching semantics for the query string beyond the rephrasing advice, so 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 (探す/検索) plus a precise resource (読み込んだページの中 from a named site) and the return shape (抜粋と URL). However it does not differentiate itself from the sibling 'search_pages', which sounds near-identical, leaving the agent to infer the distinction from the description alone.

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 explicit when-to-use ('質問されたら、まずこれを使ってください') and when-not-to-use constraints ('探せるのは読み込んだページだけ', no internet, no post-load updates), plus recovery guidance (rephrase, then admit the site doesn't cover it). It stops short of naming an alternative sibling to route to, so it lands at 4 rather than 5.

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