analyze_image

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

With no annotations, the description carries the full behavioral disclosure burden. It reveals that the calling agent cannot see the image, the default detail level, the behavior of prompt overriding task, and that save_to returns only a path + summary. It stops short of disclosing failure modes or edge cases, but the provided behavioral details are substantial.

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 well-structured with a direct opener, bullet-style source explanations, and concise notes on task/detail/save_to. Every sentence serves a purpose, and important information is front-loaded.

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?

The tool is a complex multimodal analysis function with five parameters and no output schema. The description covers all input modalities, task selection, detail level, and the save_to escape hatch. The missing explicit return format is compensated by the mention of 'detailed text description' and the save_to summary behavior, making the description sufficiently complete.

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 already has 100% parameter coverage, but the description goes further by explaining each image source option (path, URL, data URI, clipboard, raw), expanding the meaning of common tasks, and detailing how prompt overrides task and save_to alters the return behavior. This adds significant value beyond the schema alone.

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 an image with a multimodal model and return a text description. It uses a specific verb ('analyze') and resource ('image'), and explicitly notes that the agent is text-only while the vision model sees the image, which clarifies its unique role even without sibling tools.

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 usage context: it lists supported image source types, explains how to choose between predefined tasks and custom prompts, and advises using save_to for long outputs. It does not offer explicit when-not-to-use guidance or alternatives, but there are no sibling tools to contrast with.

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