capture_screenshot

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

With no annotations, the description carries the full burden and does so: it discloses the output channel (native image plus private managed file, or transient attach under autopilot with no file created), overlay hiding and restoration, temporary emulation that never spoofs the user agent or reloads, and multi-agent tab scoping with the TAB_NOT_OWNED rejection. These are non-obvious behavioral traits an agent could not get from the schema.

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 dense but front-loaded: purpose and modes come first, then inclusions/exclusions, then output and multi-agent behavior. Most sentences earn their place, though the run of behavioral clauses (emulation, overlays, multi-agent) is packed tightly and slightly increases cognitive load.

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 15-parameter tool with no annotations and no output schema, the description covers capture content, exclusions, output form, and multi-agent constraints well. It leaves minor gaps around parameter interactions (e.g., which params are valid per mode beyond the schema's own notes), but nothing critical for correct invocation is missing.

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 beyond it: tab_id should only be passed to disambiguate an owned tab, FSB overlays are hidden by default and restored, and responsive emulation is temporary and non-spoofing. It still does not explain coordinate_space or device_scale_factor semantics in prose, so it stops short of full compensation.

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 (capture) and resource (live Chromium-composited page as lossless PNG) and enumerates the four capture scopes (viewport, full document, region, element). It also draws the boundary of what is included versus excluded (browser chrome, desktop), so an agent knows exactly what this tool produces.

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?

Positions the tool for 'visual inspection and UAT' and explains how the mode/device_mode choices select behavior, which gives clear usage context. However, it never contrasts itself with close siblings like get_page_snapshot, get_dom_snapshot, or read_page, so the agent must infer when a screenshot is preferable to a DOM/page snapshot.

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