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

Annotations already declare readOnlyHint and openWorldHint, so safety and reach are covered. The description adds the concrete return shape and a hard cap of 20 results, plus the per-call cost, which is useful context. It does not disclose rate limits, latency, or failure modes for a paid external call.

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?

Two sentences, front-loaded with purpose then enriched with output fields, caps, audience and price. Dense but every clause carries signal; the enumeration of fields is slightly long but justified by the absent output schema.

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 compensates by enumerating the returned fields and the 20-result cap, and it discloses x402 pricing. Given the simple 2-param search tool this is nearly complete, missing only query-syntax guidance and any note on handling zero results.

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 50%: num is fully documented in-schema (1 to 20, default 10) while q has no description. The description's 'Up to 20 results' corroborates num but adds no query-syntax or semantics beyond the schema, so baseline 3 is appropriate.

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 (engine results page) with the SERP shape spelled out. An agent can distinguish it from search, seo, news, and report_seo because it names the exact output structure (organic_results, position, title, link, etc.).

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?

Names intended consumers (SEO, rank tracking, research agents), which implies usage context, but never states when to choose serp over the many search-shaped siblings (search, seo, news, answer) or what query patterns it handles. No explicit when-not or exclusions.

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