analyze_image

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does a good job: it mentions the ability to handle 1-9 images, supports multiple formats (local path, URL, data URI, base64), and clarifies that order is preserved and images can be compared/diffed. This goes beyond what one might assume and helps the agent anticipate multi-image behavior. However, it does not mention any potential failure modes, rate limits, or other operational details that could be relevant, though these may not be necessary for this tool.

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 exceptionally concise—two sentences that efficiently convey the core purpose, input capabilities, and typical use cases. It is front-loaded with the primary function and does not contain redundant or explanatory fluff. Every clause adds value, and the structure flows naturally from what it does to how it behaves with multiple inputs.

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 four parameters, no nested objects, and no output schema, the description covers the essential aspects: input types, count limits, ordering, and example use cases. It gives the agent enough to invoke the tool correctly for common scenarios. It does not explain when to prefer this over describe_image or ocr_image, which could be considered a completeness gap given those siblings exist, but the description still stands on its own as a complete usage guide for the tool itself.

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?

The schema description coverage is 100%, and the schema itself already thoroughly explains the parameters, including the images format, the order-preservation nuance, and the default prompt behavior. The tool description adds little beyond what the schema states. For instance, the description's note about 'compare, diff, or combine' is a rephrasing of the schema's 'compare, diff, or combine' text. Since the schema covers this ground, the description meets the baseline but does not add substantial new meaning.

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 purpose: 'Analyze one or more images with a vision model and return the text result.' It specifies a verb (analyze) and a resource (images), and indicates the output (text). However, it does not differentiate from the siblings describe_image and ocr_image, which likely serve overlapping purposes. For example, it does not explain how analyze_image is distinct from describe_image beyond the multi-image capability.

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 clear context for when to use the tool, listing use cases such as 'reading screenshots, photos, charts, UI states, document pages, etc.' This gives an agent a good sense of appropriate scenarios. However, it does not explicitly mention alternatives or exclusions, such as 'use describe_image for single images' or 'use ocr_image for text extraction only,' so the guidance is strong but not exhaustive.

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