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

Annotations already declare readOnlyHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description still earns credit for the substantive warning that results are untrusted (prompt-injection risk) — genuinely beyond the annotations. It says nothing about result caps, rate limits, or cost/pagination behavior ('free' is asserted but undefined), so it is useful but incomplete for a network 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 short sentences, front-loaded with the action and return type, followed by the safety caveat and the follow-up. Nothing is redundant and no sentence could be dropped.

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 sketch the return (URLs and snippets), which helps. But for a five-parameter, open-world search tool whose schema documents nothing, an agent is left guessing what the filters do and whether workspace scoping affects results — a meaningful gap.

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 0% across five parameters, so the description carries the full explanatory burden — yet it never mentions query, country, domains, max_results, or workspace. Bounds such as max_results 1-20 and domains maxItems 12 go unremarked, leaving filters an agent would likely want entirely undiscovered.

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 (the public web) plus the return shape (source URLs and snippets), and names the sibling research_read as the follow-up. It stops short of distinguishing itself from research_deep, so sibling differentiation is only partial.

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?

"read pages with research_read" gives explicit routing to the natural next tool, which is a real usage cue. It does not say when to prefer research_deep over this shallow search, nor any prerequisites for the required workspace parameter.

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