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

Annotations already declare readOnlyHint=true, openWorldHint=false and destructiveHint=false. The description adds real value beyond that: it discloses the corpus boundary (only loaded pages, no live updates) and prescribes non-guessing behavior on failure. It does not discuss auth, rate limits, or result limits.

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 and scope are front-loaded and each sentence carries distinct information (scope, usage, fallback, failure handling). It is a dense single paragraph rather than a tight list, so it is on the verbose side but not wasteful.

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 values need not be restated. Combined with the safety annotations, the description covers what an agent needs: what corpus is searched, when to invoke, and how to behave when results are empty. Only the relationship to search_pages is left unexplained.

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% for the single query parameter, so the baseline is 3. The description goes further by advising on query formulation — switching abbreviations to formal names or trying synonyms — which is meaningfully beyond the schema's terse example ('料金 支払い方法').

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 (search) and a bounded resource (pages loaded from securityiot.theshop.jp), with the return shape (excerpts + URLs) made explicit. It does not differentiate itself from the sibling search_pages, which appears to be a near-equivalent, so an agent cannot route between them from this text 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 clear when-to-use (use this first when asked about the site), when-not (only loaded pages, not the open web, not post-load updates), and a concrete fallback procedure (rephrase, then read returned page candidates, then admit failure rather than guess). No alternative tool is named, so tool-selection guidance is incomplete, but the contextual guidance is strong.

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