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

The annotations already mark this as read-only, idempotent, closed-world, and non-destructive, but the description adds substantial behavioral context: searching is free and counts no downloads, results are ranked by relevance, top results may not be best fits, and candidate descriptions are vision-model descriptions rather than titles. It also warns the agent not to claim it viewed an image, which is valuable operational guidance beyond 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 front-loaded with the core action and then moves through capacity, cost model, selection criteria, and ranking caveats. Despite its length, nearly every sentence adds decision-relevant information for an agent using a search-and-select workflow.

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 that an output schema exists and annotations cover safety traits, the description supplies the missing context an agent needs: catalog moderation, free search, later download step, result fields to inspect, and ranking caveats. It is complete for making correct search calls and selecting candidates responsibly.

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 searches, section, query, and limit_per_search. The description still adds strategic meaning by explaining that each group represents a distinct image need, section labels keep results straight, and candidate counts should exceed intended usage. That is useful semantic guidance beyond the already rich schema, though it does not add syntax or constraints beyond what is documented.

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 and resource: search the public, moderated ImgSearch catalog. It clearly distinguishes the retrieval step from download_images by noting that nothing is downloaded until that later call, so an agent can tell what this tool does relative to a key sibling.

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?

It gives explicit operating guidance: pass one named query group per distinct image need, use up to ten groups for multi-section work, and request more candidates than needed because downloading happens later. It also explains how to choose among results and names download_images as the follow-up action, leaving little to inference.

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