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

Annotations already cover read-only, closed-world, non-destructive behavior. The description adds valuable scope context: only previously loaded pages are searched, network-wide content and post-load updates are excluded, and it specifies expected behavior when no match is found. Return format is largely covered by the output schema.

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-loads what the tool does and the site it indexes, then layers scope limits and fallback guidance. Reasonable length but slightly dense; every sentence adds value.

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?

Comprehensive for a 1-param read-only search tool: purpose, scope boundaries, and failure handling are covered, and return values are handled by the output schema. The main gap is no differentiation from the similarly named sibling '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 coverage is 100% and there is only one string parameter with an inline example. The description adds no syntax, operators, or format detail beyond the schema. 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+resource (探す/ページ), names the site, and describes what is returned (抜粋 + URL). It does not explicitly distinguish itself from the very similar sibling 'search_pages', nor from 'fetch'/'get_page', which is a missed opportunity given this is a common naming collision.

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 clear when-to-use guidance ('質問されたらまずこれを使ってください'), scope constraints (読み込んだページのみ), and iterative fallback advice (rephrase the query, review candidate pages, don't guess if not found). An explicit comparison with sibling 'search_pages' is absent.

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