search_web_images

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

With no annotations provided, the description carries full transparency responsibility. It discloses the best-effort nature of openLicensedOnly and warns to verify usage rights, which is a critical behavioral caveat. It also details the exact output fields for each detail level (short, medium, full), offering rich behavioral context beyond a simple search statement.

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 compact, with the core purpose front-loaded in the first sentence. Each subsequent sentence serves a distinct purpose: contrast, return shape, license caveat, follow-up action, and detail semantics. No redundancy or filler is present, though it is slightly dense in the detail-parameter sentence.

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?

For a search tool with no output schema and no annotations, this description covers the essential context: search scope, return fields, license limitation, detail-level output, and downstream import workflow. Remaining parameters (gl, hl, brandId) are adequately documented in the schema, so the description is sufficiently complete without over-explaining.

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% with descriptions for all parameters, but the generic detail description ('id + primary label + status') does not match this tool's actual output semantics. The tool description corrects this by providing tool-specific meanings for detail levels (url+source, sourceUrl+alt+dimensions, raw), adding significant value beyond the schema baseline.

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 opens with 'Search Google Images across the whole web for a query', a precise verb+resource statement that immediately establishes what the tool does. It further differentiates from the sibling search_stock_images by noting this tool is broader, removing any ambiguity about scope.

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 explicitly names the alternative 'search_stock_images' for licensed stock libraries, clarifying when to use this broader web search. It also provides a clear next step by pointing to import_asset_from_url to add a result, giving actionable workflow guidance.

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