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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile needs no restating. The description adds useful context that this is legacy and returns a different format than `search`, but it does not explain what that format is, nor any limits or caveats 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 sentences, with the legacy status front-loaded so the agent hits the most decision-relevant fact first. The parenthetical aside about retaining it for existing connections is slightly redundant with the later instruction to use `search`, but nothing is padded.

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 simple two-parameter read tool with annotations covering safety, the main decision (use `search` instead) is fully covered. The gap is that the differing return shape is asserted but never described, and there is no output schema to fill that in, so an agent choosing this tool cannot know what it will receive.

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 description says nothing about either parameter. The schema documents `query` but leaves `limit` (default 5, max 20) undescribed, so at 50% coverage the description should compensate for the gap and does not.

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?

The description names a concrete verb and resource ('サイトの中を探す' - search within the site) and explicitly distinguishes this tool from the sibling `search` by stating the return shape differs. The only remaining ambiguity is that it never says what the different return shape actually looks like, so an agent knows the category but not the output.

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 gives an explicit when-not-to-use ('新しく使うときは search を使ってください' - use search for new usage) and a when-to-use ('すでにつないでいる人のために残しています' - kept for those already connected). The alternative sibling is named along with the condition that selects it, leaving no inference required.

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