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

Annotations already cover the safety profile (readOnlyHint, openWorldHint=false, destructiveHint=false), and the description adds genuinely new behavior: only indexed/loaded pages are searchable, post-load updates are excluded, and a prescribed anti-hallucination fallback when nothing is found. That is meaningful context beyond the structured fields.

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 is searched and the trigger for using it, then layers scope limits and the retry/fallback ladder. It is somewhat long, but nearly every sentence adds actionable information about scope or recovery behavior.

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?

Covers scope, freshness limits, retry strategy, and fallback, and an output schema exists so return formatting need not be described. The main gap is that it does not differentiate itself from the equally named sibling search_pages, which is the most likely source of misselection.

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 implies multi-word/searchable terms but adds no syntax, matching, or tokenization details beyond the example already present in the schema.

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 resource (pages loaded from 買取大陸/kakeruyone.com) and describes the return (excerpt + URL), which is more than the generic name 'search' conveys. However, it never distinguishes this tool from the sibling 'search_pages', which an agent could easily confuse with it.

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 usage 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'), clear scope limits, and a concrete retry procedure (rephrase, expand abbreviations, try synonyms) plus a fallback instruction not to guess. It does not, however, state when to prefer fetch/get_page/search_pages instead, so the routing versus siblings is left implicit.

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