browser_screenshot

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

With no annotations, the description carries the burden. It discloses the save location, path resolution rules, and full-page behavior, which is useful. However, it leaves unclear whether the tool returns the image inline, writes only to disk, how return_base64 affects behavior, or any side effects like overwriting existing files.

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 organized with Purpose, Constraints, and Example sections, making it scannable and front-loaded. It is not overly verbose, though the truncation in the purpose text prevents a perfect score.

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 tool with 5 parameters, no output schema, no annotations, and a non-trivial save behavior, the description is incomplete. It omits key parameters (annotate, return_base64), the nature of the inline image content, and the full return behavior, making it hard for an agent to invoke correctly in all 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?

Schema description coverage is 0% and the description must compensate. It explains full and partially explains path and session, but annotate and return_base64 are completely unexplained. The example with session='recon' helps, but not enough for a 5-parameter tool.

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?

The description clearly states the tool captures a validated PNG screenshot of the current page as MCP image content and saves it, which is specific and actionable. It does not explicitly differentiate from sibling browser_snapshot, but the verb and output format make the core purpose clear.

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 provides practical constraints (default save path, path traversal restrictions, full-page capture via full=True) that imply when these options matter, but it does not explicitly state when to choose this over sibling tools like browser_snapshot or browser_read. No exclusions or alternative recommendations are given.

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