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 is covered; the description complements that by disclosing the real limits an agent would otherwise hit (a fixed snapshot of already-loaded pages, with neither the wider web nor post-load updates visible). It also reveals fallback behavior: when nothing matches it returns candidate pages, and the agent is told not to guess beyond that. It stops short of describing result ordering, pagination, or hit counts.

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?

The purpose and scope are front-loaded in the first two sentences, and the remaining sentences each carry actionable instructions for the retry and miss path. It is somewhat long for a one-parameter search tool, but no sentence is filler: even the closing instruction against guessing changes how the agent responds to an empty result.

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?

The definition covers what the agent must know beyond the structured fields: the data boundary (loaded pages only), how to retry, and how to handle a no-match. The output schema means the description needs no explanation of return values, and the annotations mean it needs no safety caveats. Only the relationship to the sibling tools is left unaddressed.

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% and the single 'query' parameter already ships its own description and example, so the schema does the heavy lifting. The description adds only indirect hints about how queries are matched: it advises rephrasing the query with expanded abbreviations or synonyms, which implies plain keyword matching rather than operators or structured filters. Since there is only one parameter, that is close to the baseline.

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 gives a concrete verb and resource: it searches the text of pages previously loaded from codenate.jp and returns matching passages with excerpts and URLs. The scope is precisely bounded (loaded pages only, not the broader web). However, it never distinguishes itself from the sibling tool 'search_pages', which by name sounds like it does the same thing, so an agent cannot rule that sibling out without opening both schemas.

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 states explicitly when to reach for this tool (questions about CodeNate-こうでねーと- should start here), what it cannot cover (the open web, content updated after loading), and even prescribes a retry strategy: rephrase using expanded abbreviations or synonyms, then read the candidate pages returned on a miss before admitting the answer was not found. The only gap is that it never names the alternative sibling tools it should be preferred over or deferred to.

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