browser_screenshot

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

With no annotations supplied, the description carries the full disclosure burden. It does add one genuinely useful constraint (writes are confined to the harness directory, no arbitrary file writes), but says nothing about whether the capture is viewport-only or full-page, what format is produced, whether a path or inline image is returned, or how failures surface.

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, no filler, with the security-relevant scoping constraint placed immediately after the action. Nothing is redundant.

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 zero-parameter tool with no annotations and no output schema, the description should still tell the agent what comes back (file path, image payload, or acknowledgment) so it knows how to use the result. The write-location constraint is covered, but the return behavior is left entirely undocumented.

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?

The schema has zero parameters, so the baseline is 4; there is nothing to disambiguate. The description could usefully have noted the implicit fixed behavior (no filename, no format, no full-page flag can be requested), but the absence of parameters keeps this unproblematic.

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 concrete verb and resource ('Save screenshot') plus the destination constraint ('local browser harness directory'), which is specific enough to separate it from interaction siblings like browser_click or browser_read. It does not distinguish itself from browser_snapshot, which an agent might reasonably confuse it with.

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 name and phrasing imply when the tool applies (capturing a visual of the current page), but there is no explicit when-to-use statement, no mention of page state prerequisites, and no named alternative such as browser_snapshot. Usage is inferable but not guided.

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