Capture page screenshot

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds valuable behavioral context by stating the screenshot is bounded in-memory, uses measured CSS-pixel clips, performs encoded-byte validation, and does not write to caller-controlled paths or inspect other sessions. This adds meaning beyond the annotations, justifying a 4.

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 a single paragraph of about three sentences, front-loaded with the core action and then detailing constraints. It is compact with no filler, but it could be more structured (e.g., bullet points) to separate capture modes. Still, it is efficient and earns a 4.

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 is moderately complex with several capture modes and iframe support, but the schema and output schema provide substantial detail. The description covers scope, bounds, and safety without needing to explain return values. It misses some edge-case guidance (e.g., what happens on invalid locators), but given the richness of the schema, it is complete enough for an agent to act 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 0% according to context, so the description must carry the load. The description mentions 'explicitly addressed page' and 'bounded iframe chain,' which clarifies the frame parameter and element selection, but it does not explain the semantics of sessionId, pageId, or timeoutMs exhaustively. Since the schema itself is rich with enums and descriptions for those fields, the description adds only marginal value, so a baseline 3 is appropriate.

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 clearly states the tool captures a bounded screenshot of a single page or element, with specific modes (viewport, full page, element) and constraints. It distinguishes itself from siblings like observe or snapshot by focusing on image capture, and the description's specificity (e.g., 'bounded in-memory PNG') makes the purpose unmistakable.

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 description implies usage by specifying capture modes and options like iframe chains, and states a key limitation: it does not write to caller-controlled paths. It does not explicitly mention alternatives or when not to use it (e.g., for text extraction), but the context is clear enough for an agent to infer appropriate use cases, so it earns a 4 rather than 5.

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