visual_diff

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

With no annotations, the description carries the full burden. It discloses the return shape (changed pixel count and percentage) and a dependency fact (Playwright not required), which is genuinely useful, but says nothing about whether a diff image is produced, side effects, or processing limits for large images.

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?

Three short sentences with zero filler; the core action is front-loaded and each sentence adds a distinct fact (action, return, dependency).

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 two-image comparison tool with no output schema and no annotations, the description covers the action, inputs (base64 PNGs, inferable from schema), and return summary. It is nearly complete, only lacking detail on the optional threshold's effect and whether image artifacts are emitted.

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 100%, so the threshold, before_image, and after_image parameters are already documented in the schema. The description adds no additional parameter meaning (e.g., how threshold interacts with the reported percentage), so the baseline of 3 applies.

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?

States a specific verb and resources ('Compare two PNG screenshots pixel-by-pixel') plus the domain ('visual regression testing'). No sibling tool does image-to-image comparison, so the agent can route to it without opening the schema.

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 'for visual regression testing' phrase implies the use case, and 'Does not require Playwright' hints at an alternative execution path, but no explicit when-to-use vs when-not guidance or named alternative tool is given.

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