Screenshot as escalation

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial behavior the structured fields cannot: the coverage report semantics, 'status partial' when unreadable iframe regions or shadow roots intersect the viewport, the explicit warning that 'no-known-omissions' is only an iframe check and not a fidelity guarantee, and that blank areas or placeholders do not mean the frames are empty. That is unusually rich limitation disclosure.

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 routing rule is correctly front-loaded, but the prose is dense and meandering, with jargon-heavy clauses like 'capture identifies the renderer and pinned engine version, commit and SHA-256' that force the reader to parse what 'capture' even refers to. Several sentences could be tightened without losing meaning.

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?

No output schema exists, so the description carries the return-content burden, and it does so well by describing the coverage report, partial status, and renderer/engine identification. The remaining gap is minor: it never states the image or artifact format an agent should expect back.

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 both parameters (id, sessionId) are already fully documented structurally. The description only reiterates element centering and adds nothing about id format or session resolution semantics. Baseline 3 applies when the schema carries the parameter burden.

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 (SnapDOM render of the viewport, optional element centering) and explicitly frames itself as an escalation rather than a default capture. It also draws a boundary against siblings: 'native browser screenshots are separate diagnostic evidence' and 'for what changed there is browser_verify.' An agent can distinguish it from browser_verify and browser_diff without opening any 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?

Gives an explicit when-to-use condition ('Only when the doubt is genuinely visual — layout, color, overlap') and a named alternative for the excluded case ('for what changed there is browser_verify'). The escalation framing makes the cost/benefit tradeoff clear to the agent.

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