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

With no annotations provided, the description carries the full transparency burden. It explains result fields, news fallback to web, engine fallback behavior, and the cost per call, making the tool's behavior quite predictable.

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 description is dense and information-rich, but it is written as a long run-on paragraph with many embedded clauses and parentheticals. It could be clearer with structured bullets or separated option lists, though no sentence is pure filler.

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?

Given the tool's complexity, the description covers the main behavior, all major options, fallback behavior, and an example call. It does not describe error cases, but it provides sufficient context for an agent to invoke the tool correctly.

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?

The schema only exposes a generic 'params' object, but the description fully documents the accepted parameters and their value formats, including q, num_results cap 25, region, timelimit, safesearch, page, mode, and engine. This fully compensates for the opaque 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?

The description clearly identifies the tool as a keyless web search returning ranked title, URL, and snippet, and enumerates its search options. It is distinguishable from the sibling tools by its explicit 'SERP' purpose, though it does not explicitly contrast itself with serp_batch/serp_multi/serp_read.

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 provides a concrete example and recommends the 'auto' engine, including fallback behavior when pinned engines fail. However, it does not explicitly say when to choose this tool over related sibling search tools like serp_batch, serp_multi, or serp_read.

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