search_bulk

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: asynchronous execution, deduplication, retention of page-one enrichments, the effect of setting render:true, and billing logic with refunds. It does not mention rate limits or authentication, but it covers the operational traits an agent needs to know before invoking, so it is strong.

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?

Three sentences with zero filler. The main function is front-loaded, then the enrichments and billing are stated compactly. Every sentence earns its place; no redundancy.

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 (16 parameters, async execution, billing), the description is reasonably complete but omits critical operational details. It does not explain how to retrieve the results (e.g., job ID or status endpoint), nor the output format. The sibling 'search_bulk_status' suggests there is a status mechanism, but the description does not mention it, leaving an agent to infer the interaction pattern.

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 100%, so baseline is 3. The description adds meaning by linking 'render:true' to the capture of Google JS blocks (a functional hint), and clarifies billing per page which affects usage. It does not elaborate on other parameters like wait_for or google_params, but the added hints are beneficial and go beyond simple schema descriptions.

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 states a specific verb ('Paginate') and resource ('ONE search query'), and explicitly mentions the async, deduplicated, and merged nature of organic results. It clearly distinguishes itself from a single-page search tool by emphasizing pagination and consolidation, making it easy for an agent to differentiate from siblings like 'search'.

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 paginating a search across multiple pages, but it does not explicitly compare with alternatives like 'search' or 'search_and_read'. There is no 'when to use' versus 'when not to use' guidance, nor mention of the status-tracking sibling tool. The context is clear that it is for bulk retrieval, but lacks explicit routing.

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