screenshot

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

Annotations already declare readOnlyHint and openWorldHint, and the description still adds substantive behavior: default jpeg quality 70, long edge capped at max_edge (1280), the fact that annotate overlays are removed before returning (so the caller must not expect them to persist), and that save writes under <output-dir>/screenshots/. What is missing is what the call actually returns when save is false.

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?

Four dense sentences with no filler, front-loaded with the capture modes before the defaults and side effects. The telegraphic phrasing ("Default jpeg quality 70, long edge at most max_edge") is efficient but costs some readability.

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 an 8-parameter tool with no output schema and thin schema descriptions, the definition covers behavior well but leaves two real gaps: what is returned when `save` is false (image payload? path? reference?), and what `target` accepts (CSS selector, snapshot ref, coordinates). An agent can call it, but not confidently predict the response.

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 coverage is only 13% (just `tab`), so the description must carry the load and largely does: it supplies defaults and meaning for quality (70), max_edge (1280), full_page, target, annotate, and save. `format` is left to the schema enum and `target`'s accepted form (selector vs. ref) is never specified.

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 first sentence names a specific verb and resource and enumerates the three capture modes (viewport default, full page, target element), which is exactly what an agent needs to decide between this and a non-visual sibling. It does not, however, explicitly distinguish itself from `snapshot` or `video`, so the boundary with those siblings is left to inference.

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?

"Afterwards, 'x,y' targets use this image's pixel coordinates" is genuine cross-tool guidance linking the screenshot to click/drag/hover, but it only covers the post-capture workflow. There is no statement of when to prefer screenshot over `snapshot` (DOM/accessibility) or `video`, and no exclusions or prerequisites.

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