gemini_vision

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

Annotations already declare readOnlyHint=true, so the agent knows it's a safe read operation. The description adds valuable behavioral detail: local image paths are read and sent to a proxy, while URLs are passed without local fetching. This clarifies how the tool handles different input types and potential network implications, going beyond the annotation.

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 a single sentence with no wasted words. The core purpose is front-loaded ('Analyze or compare up to four images'), followed by a concise behavioral note. Every word earns its place, making it highly efficient.

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 tool with only two parameters and no output schema, the description is mostly complete. It covers the essential purpose and input behavior. The main gap is the lack of any mention of what the response contains (e.g., a text analysis result), which might be important for an agent to set expectations. However, given the simplicity and annotations, it is adequate.

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 0%, so the description must compensate. It explains the images parameter's behavior (local paths vs URLs) and mentions 'up to four images,' which aligns with maxItems. However, it does not describe the prompt parameter's purpose, though that is relatively self-evident. It adds meaningful context for images but not fully for prompt.

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 clearly states the tool's function: 'Analyze or compare up to four images.' It uses a specific verb (analyze/compare) and resource (images), and implicitly differentiates from siblings like image_generate (which generates rather than analyzes) and gemini_flash (likely a different model). The purpose is unambiguous.

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 provides no explicit guidance on when to use this tool versus alternatives like gemini_flash or image_generate. It does not mention exclusions, prerequisites, or conditions under which another tool would be preferred. The only contextual hint is the tool's name and description, which imply image analysis, but no direct comparison is made.

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