Dock screenshot

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

The description adds real behavioral context beyond the annotations: output format (JPEG), the fact that it 'Works in a background tab' (not obvious for a capture tool), and the default downscaling clamp. It does not, however, address the annotations' readOnlyHint=false / destructiveHint=true, so an agent gets no reconciliation of why a screenshot is flagged destructive, nor any note on payload size or how the image is returned.

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?

Two compact sentences: output scope first, then engine/tab behavior, then the routing decision. Every clause carries information and nothing is repeated from the schema.

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?

With no output schema, the description correctly covers the return shape (JPEG), the unit of capture (viewport or element), and the width cap. It is nearly complete for a capture tool; only the delivery mechanism and any size/pagination constraints go unstated.

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 ref, tab_id, quality and max_width are already fully documented in the schema and the baseline is 3. The description reinforces two of them ('or one element: ref', 'at most max_width px wide') but adds no syntax or format detail the schema lacks.

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 — it returns 'A JPEG of the tab's visible area (or one element: ref)' — and explicitly contrasts itself with the sibling dock_snapshot. An agent can distinguish it from dock_snapshot and dock_text without opening a 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 both the when-not and the alternative: 'Prefer dock_snapshot for acting — use this when layout or images matter.' The routing condition is explicit rather than inferred, and it also notes the background-tab precondition.

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