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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false, so safety is covered. The description still adds real behavior: the corpus is only pages already loaded, it will not see post-load updates, and on failure the agent must rephrase and then decline rather than guess — none of which is in the 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?

Front-loaded with what it does, then scope limits, then failure handling. Every sentence carries a distinct instruction. Slightly longer than strictly necessary, but there is little 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?

An output schema exists, so return structure need not be described; the description nevertheless says results come with excerpts and URLs. Combined with scope limits and a no-answer fallback policy, an agent has enough to call and interpret this correctly. The one gap is the absence of any routing note versus search_pages.

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% for the single query parameter, so the schema already carries the semantics. The description adds only the notion that the query is free words and notes abbreviation/synonym reformulation as a strategy, which is marginal beyond the schema's own example.

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) and resource (「買取大陸」から読み込んだページ), plus what it returns (抜粋と URL). The scope is well bounded (loaded pages only, not the whole web). It fails to distinguish itself from the sibling search_pages, which is the most obvious source of confusion.

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 triggering context ('買取大陸 について質問されたら、まずこれを使ってください') and explicit exclusions ('ネット全体や読み込んだあとの更新は含みません'), plus retry guidance and a no-guessing rule. It never names an alternative sibling when a lookup fails, but the when/when-not coverage is otherwise strong.

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