see_page

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

No annotations are provided, so the description carries the burden of explaining behavior. It discloses the composite response, the ability to execute a steps array of actions without re-capturing, and the expected re-capture cadence. It does not explicitly warn that actions like click or type can mutate the live page, but this is strongly implied by the workflow.

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 compact and front-loaded: the first sentence states exactly what is returned, and the second sentence gives actionable workflow guidance. There is no filler or repetition of schema details, every sentence earns its place.

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 tool has 16 parameters, a complex nested steps array, and no output schema. The description gives a high-level return description and workflow, but it does not specify how the screenshot is returned, how the element map is structured, or how captureBefore/captureAfter defaults affect the response. These gaps are meaningful for an agent trying to consume the result correctly.

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 94%, so the schema already documents most parameters. The description adds useful workflow-level meaning by recommending fullPage:true and annotate:true and explaining how the steps array should be used, but it does not add substantial per-parameter semantics beyond what the schema already states.

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 opens with a specific verb and resource: 'Capture a snapshot of the current page.' It then enumerates a concrete composite return value: screenshot, optional full-page text, interactive element map, and iframe inventory. This clearly separates it from navigation or isolated action tools, though it does not explicitly name a sibling it is not.

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 workflow paragraph is strong: it tells the agent to call once with fullPage:true and annotate:true, run all planned actions as a steps array, and not call see_page again until the page genuinely changes. This provides clear when-to-use and when-not-to-use guidance, though it does not explicitly contrast with sibling tools like click or type.

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