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

Annotations already cover read-only and non-destructive behavior. The description adds legacy/deprecation status and warns that the return format differs from `search`, which is not visible in the annotations. It could specify the return shape further, but it adds meaningful behavioral context beyond 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?

Three short Japanese sentences, each earning its place: what it is, how it differs from `search`, and which tool to use instead. No filler or repetition of schema content.

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 read-only legacy search tool with two simple parameters, the description adequately explains what it does, how it relates to `search`, and what a new caller should do. The unspecified return format is a minor gap, but the explicit redirect to `search` makes it non-critical.

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?

The schema covers `query` with an example, but `limit` has no description; the tool description adds no parameter-level detail to compensate. However, the parameters are simple and the default/min/max constraints provide enough guidance for correct invocation.

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?

Description clearly states it searches inside the site ('サイトの中を探します') and explicitly identifies itself as the old-name version of `search` with a different return form ('返す形が違います'). This makes its purpose concrete and differentiates it from the sibling `search`.

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?

It explicitly says new users should use `search` instead ('新しく使うときは search を使ってください') and explains it is kept only for those already connected ('すでにつないでいる人のために残しています'). This gives clear when-to-use and when-not-to-use guidance.

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