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

Annotations already declare readOnly, idempotent, and non-destructive, so the safety profile is covered. The description usefully adds the return format (WebP, one image per call) and the tie to structured evidence, but omits resolution, size, and error behavior when the file is missing or a non-image (e.g. the .json example in 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?

Two sentences, front-loaded with the return type, then the usage note. The enumerated scope list is long but each item carries real distinguishing information rather than filler.

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?

An output schema exists, so return values need no explanation, and the schema carries full parameter sourcing detail. The description adequately covers what the tool fetches and why; only fallback/error behavior is left implicit.

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 every parameter (file, page, view, product, version, environment) is already documented with sourcing guidance. The description adds no parameter-level meaning beyond the schema, so the baseline 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 resource (return one evidence WebP for a page view) and enumerates the exact categories of image it can return: component states, hover/click reveals, alternate color scheme, extra viewport width, embedded frame. This lets an agent distinguish it from generic image siblings like get_page_image, though no sibling is named explicitly.

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?

"Use for visual checks of what the structured evidence describes" gives an implied workflow (fetch the image after reading the structured evidence), but names no alternative or exclusion. With ~9 sibling image-fetching tools, the agent gets only partial routing guidance.

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