browser_screenshot

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

There are no annotations, so the description carries the full burden, and it does disclose two real behaviors: a file is written to local disk and the return value is an image for multimodal inspection. It omits where the file is written, whether an existing file is overwritten, and the default naming behavior (only the schema mentions the timestamp default). Reasonable but not complete for an un-annotated tool with a disk side effect.

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 short sentences that front-load the action and the return payload before the mode options. No filler, though the mode sentence slightly duplicates the schema's own parameter descriptions.

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 zero required parameters, a fully documented schema, and no output schema, the description covers what an agent needs: it returns an image and supports three capture scopes. Missing only minor operational detail such as the save location, which matters little for a screenshot call.

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 100%, so all three parameters (ref, filename, fullPage) are already explained in the schema, including the defaults. The description's restatement of the same three modes adds essentially no new meaning such as ref format expectations or filename collision behavior, so the baseline of 3 applies.

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 a screenshot and save it locally) plus what is returned: an image for multimodal viewing. It also enumerates the three capture scopes (full page, viewport, single element). It stops short of naming a sibling such as browser_snapshot as the non-image alternative, so sibling disambiguation is left to inference.

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 through the mode list – use ref for one element, fullPage for the whole document, otherwise the viewport – which is useful guidance. However, it never states when to prefer this over browser_snapshot or other inspection tools, and gives no prerequisites such as needing a navigated page or a valid ref from a snapshot.

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