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

Annotations already cover safety (readOnlyHint, idempotentHint, destructiveHint=false), and the description goes well beyond them: whole-word case-insensitive matching, the strict-then-relaxed matching rule, the `relaxed` flag, ranking by match quality, a 20/50 row cap with no pagination, and empty rows returned instead of an error. This is unusually rich behavioral disclosure for a search tool.

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-loaded with purpose and the example queries, followed by return shape then matching semantics. It is dense and every sentence carries information, but it is delivered as one long unstructured paragraph, making the return-field list harder to scan than a short bulleted shape.

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?

There is no output schema, and the description compensates fully by enumerating every returned field (`query`, `relaxed`, `total`, `shown`, `rows` and each row's type/tool/value/unit/quote/sourceUrl/checked/page). Combined with the empty-result behavior, an agent has everything needed to call this and interpret the response.

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% so the baseline is 3, but the description adds meaning the schema does not: what 'relaxed' means for `query` matching, the whole-word case-insensitivity rule, no operators, and that `limit` is a ranked quality cut (max 50, default 20) with no pagination. That is genuine value over the enum/text definitions.

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 concrete verb and resource: 'Read-only keyword search across every plan, limit, rate, free tier, overage rule and gotcha in all datasets.' It explicitly distinguishes itself from siblings by naming list_tools and get_tool as follow-ups, so an agent can tell it apart from compare_tools/list_changes without opening a schema.

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?

Explicitly declares itself the 'Best first call' and gives three concrete example questions that should route here. It also names the fallback path ('then try list_tools to find the product id and call get_tool') for the empty-result case, which is a real when-to-use/when-not distinction.

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