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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered; the description adds real value beyond that by disclosing the ranking tiers, the stemming/English fallback behavior, the returned fields, and the 20-row cap against `total`. It does not mention auth requirements or how to retrieve rows beyond the first 20, which keeps it short of a 5.

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 whole definition is a single dense run-on sentence stitched together with semicolons and a colon, with the core purpose buried mid-sentence rather than front-loaded. The content is largely non-redundant, but the structure makes it hard to scan quickly.

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?

With no output schema, the description does the work of explaining return values: path, url, title, description, matching passage, and the 20-of-total limit. For a read-only search tool with fully covered parameter schemas, this is close to complete, though pagination behavior and auth expectations are left implicit.

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%, so all three parameters (site, query, token) are already documented in the schema, including the token-header fallback. The description adds output shape and the 'first 20 of total' limit but nothing new about parameter syntax or formats, so the 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?

The description describes the result set ('the site's pages that hold some words') and the ranking order, so the resource is identifiable, but it never states the action as a verb and never differentiates itself from siblings like read_page, get_site, or wiki_history. The purpose is inferable from the name rather than stated in the text.

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?

There is no when-to-use guidance, no mention of when to pick this over read_page or get_site, and no explanation of when the `site` or `token` parameters are required. The equivalence to '/search.json?q=' hints at a context, but the agent is left to infer everything else.

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