browser_search

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

Annotations already provide safety and side-effect hints (readOnlyHint=false, idempotentHint=true, openWorldHint=true, destructiveHint=false). The description adds meaningful behavioral context beyond these: it reads results in parallel tabs and ranks them against the goal. This clarifies that the tool opens tabs and processes results, which is not covered by annotations. No contradictions with annotations.

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 a single, concise sentence that front-loads the primary action (search) and includes the main purpose (read and rank). There is zero wasted text, and every word contributes to understanding. This is an exemplary model of conciseness.

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?

The tool has three parameters and no output schema or parameter descriptions. The description covers the high-level behavior (search, read, rank) but omits details such as what 'best results' means, how max_pages influences the process, and what the return format is. Given the tool's relative simplicity, the description is adequate but not fully complete; an agent would need to infer some details or rely on the parameter names.

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%, so the description must compensate. It explains the 'goal' parameter (used for ranking) but leaves 'query' and 'max_pages' undefined. 'max_pages' is particularly ambiguous—it likely controls how many results to read, but the description doesn't say this. The description only partially clarifies parameter semantics, leaving significant gaps.

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 states the tool's purpose: search the web, read best results in parallel tabs, and rank against a goal. This distinguishes it from sibling tools like browser_act or browser_click, which focus on page interaction rather than search and ranking. The verb 'search' and the resource 'web' are specific and unambiguous.

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?

The description implies usage for information retrieval and ranking, but does not explicitly mention when to avoid it or use alternatives. The context is clear (search the web), but there are no exclusions or named alternatives. Since the sibling set includes many interaction tools, the description's focus on search inherently suggests the use case, but it doesn't spell out when not to use it.

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