vision_inspect

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

With no annotations, the description carries the full burden. It discloses auto-detection of input formats via image_source, lists backward compatibility parameters, and explains the mode options. However, it does not mention side effects, error behavior, or safety profile (e.g., read-only nature), which would be relevant for a tool that processes user-provided images. Still, it adds meaningful behavioral context beyond the schema.

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, front-loaded with the core purpose, followed by usage exclusions, input format guidelines, and an Args list. Every sentence serves a purpose, and the bullet-like format makes it easy to scan. Despite covering 9 parameters, it remains compact and free of fluff.

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 the tool's complexity (9 parameters, 0% schema coverage, no annotations), the description provides near-complete context: it covers all parameters, explains the recommended input source, lists mode values, and gives clear sibling distinctions. An output schema exists, so not explaining return values is acceptable. No major gaps remain.

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 does so thoroughly: every parameter is listed in the Args section with a concise explanation, and image_source gets extra detail with concrete format examples (local path, URL, data URI, plain base64). This adds substantial meaning beyond the bare schema titles.

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 starts with a specific verb and resource: 'Analyze a single image' and lists concrete use cases (screenshot understanding, UI analysis, chart comprehension, error extraction). It explicitly distinguishes from siblings by naming vision_diff and vision_crop_verify as alternatives for excluded tasks, making the tool's purpose 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 states clearly when to use ('Use this tool ONLY when the user has an image and wants to understand its content') and when not to use it, naming the alternative tools for two specific excluded scenarios. This provides explicit usage context and differentiation from siblings.

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