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

With no annotations provided, the description carries full burden. It discloses that the tool returns a similarity score and changed-pixel count as text, and also returns baseline, live, and diff images for direct viewing. It explicitly states that the tool does not make the judgment call for the agent, which is a crucial behavioral trait. It also hints at the nature of the comparison (perceptual pixel-diff) and gives examples of benign noise, providing transparency about limitations.

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 long but well-structured and front-loaded. The first sentence states the core purpose and method. It then details the return values and input modes, followed by interpretation guidance. Every sentence contributes value; there is no filler. It is appropriately sized for a tool with multiple input modes and complex output.

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 description is complete for an agent to use correctly. It explains the two input modes, the required parameter, the return format (text and images), and how to interpret the results. It references the sibling list_visual_reviews for obtaining a review_id, which is sufficient. No output schema is present, but the description covers return values. There are no obvious gaps in what the agent needs to know.

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 descriptions already cover all parameters (100% coverage), so the baseline is 3. The description adds value beyond the schema by explaining the either/or relationship between baseline_image_base64 and review_id, and by clarifying that images must be raw base64 without a data: prefix. It also notes that review_id pulls a stored baseline, which is not fully clear from the schema alone. This justifies a 4.

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: 'Compare two screenshots — a baseline/expected capture and a live/current capture — using a perceptual pixel-diff.' It specifies the verb (compare), the resource (screenshots), and the method (perceptual pixel-diff). It also distinguishes itself from siblings by explaining it returns both a score and images for the agent to judge, and it references list_visual_reviews for an alternative input mode, setting it apart from other visual 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 explicitly states when to use the tool and how to choose between two input modes: 'Provide either two raw base64 images, or a review_id (from list_visual_reviews) to pull a stored baseline instead of re-fetching it.' It also explains the purpose of the returned images and guides the agent on interpreting results (real regression vs benign noise). This is direct usage guidance with clear alternatives.

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