screenshot

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

With no annotations provided, the description carries the full behavioral burden and handles it well: it discloses that the image comes back inline (saving a round trip), that a local path is also saved to disk, and that return_image=false switches to path-only output. It does not cover failure modes or where the saved file lives, but the core side-effect profile—writes to disk and embeds image data—is clearly surfaced.

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?

Three short sentences, each earning its place: the action and scope, the key inline-return benefit, and the toggle for path-only. It is front-loaded with the verb and resource, with zero filler or repetition of schema boilerplate.

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 a 5-parameter tool with no required fields and full schema descriptions, the description covers the essential behavior, the return shape (inline image + path), and the main configuration switch. The missing pieces—on-disk path details, invalid-ref behavior, and explicit guidance vs the snapshot sibling family—are gaps, but they are minor against a schema that already documents every parameter fully.

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 100%, so the baseline is 3, but the description adds real meaning: it explains the ref/selector relationship in prose and introduces the 'no second Read call' benefit, which gives the return_image parameter behavioral significance beyond the schema's bare 'Embed the PNG in the response.' The modal-use-case hint also contextualizes element capture.

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 uses a specific verb and resource ('Screenshot the page, or a single element with ref/selector') and clearly distinguishes two capture modes: full page vs element-level. It stops short of a 5 because it does not explicitly differentiate itself from sibling tools like browser_snapshot or the various *_and_snapshot combinations, though the inline-image emphasis partially compensates.

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 when to use it: when you want an inline image without a second Read call, or element-level capture ('great for documenting one modal'), and the return_image toggle clarifies a path-only variant. However, it never names alternatives or states when not to use it, leaving the agent to infer the boundary against screenshot-adjacent siblings such as browser_snapshot and navigate_and_snapshot.

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