image_search

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: results stay fresh for 30 minutes, provider-specific result limits (Brave up to 200, Google up to 10), and filter caveats that vary by provider. This materially helps an agent set expectations.

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?

Every sentence earns its place: the first states the core function and filters, the second gives result limits, and the third gives the primary alternative and freshness caveat. The most important information is front-loaded, and there is zero filler.

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 an 11-parameter tool with an output schema, the description covers the essential decision-relevant context: what it returns (image links), provider-specific limits, when to use it, when not to, and a caching/freshness caveat. Combined with the rich schema and annotations, nothing critical is missing for an agent to invoke this correctly.

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%, and the schema provides detailed descriptions for all parameters including enum values and provider-specific behavior. The description summarizes filter categories and provider differences, but does not add meaning beyond what the schema already supplies. The baseline of 3 is appropriate because the schema carries the semantic weight.

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 the specific action and resource: 'Find images on the web matching your description.' It clearly differentiates from web_search by stating it is best for visual references/assets, and even names the sibling tool that should be used for text content. This makes the purpose unambiguous and distinct.

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 provides use guidance: 'Best for finding visual references or assets — use web_search if you need text content from pages that contain images.' This directly tells the agent when to pick this tool over its sibling, leaving no ambiguity about the intended use case.

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