search

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses automatic site-search detection vs. Google fallback, that it returns a results status, multi-agent tab scoping, the TAB_NOT_OWNED cross-agent rejection, and a concurrency cap (default 8, range 1-64). It does not cover permissions/auth or whether the search mutates page state.

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 opening two sentences are redundant, with the "When to use" clause re-stating the purpose verbatim. The remaining content (detection heuristics, related tools, multi-agent semantics) is dense and earns its place, but the front-loaded duplication wastes the most prominent position.

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?

No output schema exists, and the description gives only "Returns search results status" as a return-value hint, which is thin. However, it compensates with rich operational context: detection behavior, sibling tool routing, and multi-agent tab ownership rules. For a 5-param browser-automation tool with zero annotations, this is close to complete but leaves return format and failure modes underspecified.

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 100%, so the schema already documents query, client, tab_id, is_final, and visual_reason in detail. The description's tab_id guidance (pass only when the agent owns multiple tabs; auto-resolves otherwise) largely duplicates the schema text. Baseline 3 is appropriate when the schema does the heavy lifting.

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 and resource ("Search for content on the current site or web") and adds mechanism detail (DOM heuristic detection of site search inputs, Google fallback). An agent can distinguish this from sibling search tools like search_memory and search_capabilities, though that differentiation is left implicit.

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 "When to use" clause merely restates the purpose ("to find content on the current site or web"), which is circular rather than directive. It does, however, name follow-on tools (read_page, click) and describe the search-then-read-then-click flow, giving implied sequencing. No explicit when-not or alternative selection criteria are given.

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