browser_screenshot

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

With no annotations the description carries the full burden, and it does disclose non-obvious behavior: output is a PNG with image-to-viewport CSS coordinate mapping, full-page capture may require scrolling before further input, and background rendering can stall. It omits whether the image is returned inline or as a handle/resource, which matters for a no-output-schema tool.

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?

Four tightly packed sentences, mode and constraint information front-loaded, with no filler. Some phrasing is telegraphic ('image-to-viewport CSS mapping', 'Full-page points') and costs a re-read, which keeps it below top marks.

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 10-parameter tool with a nested frame object, no annotations and no output schema, the description covers modes and constraints but leaves major gaps: where 'ref' values originate, what the nested frame selector does versus frame_id, and how the PNG is delivered. An agent could still invoke it, but not confidently in frame or element-targeting scenarios.

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?

At 70% schema coverage the description contributes real semantics that the schema cannot express: the mutual exclusivity of full_page and element capture, and the rule that locator options (ref/name/nth/frame_id) require selector. Undocumented parameters such as ref and tab_handle are not explained, and the meaning of 'ref' (presumably from browser_snapshot) is left to inference.

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 ('Capture ... as PNG') and enumerates the three capture modes (viewport, full_page, single ref/selector element), which is far more than a restatement of the name. It only implicitly separates itself from visual/text siblings via the 'use AX/text' fallback, and never names browser_snapshot or browser_read_text.

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 concrete selection rules: element vs full_page are exclusive, locator options require selector, and stalled background rendering should be handled by activating the tab or switching to AX/text. It lacks an explicit 'use this when you need visual confirmation' framing, but the exclusions and fallback path are clear.

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