chrome_screenshot

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

With no annotations, the description must carry the transparency burden. It discloses automatic resizing and returns base64 PNG with metadata, but does not specify viewport vs full-page capture, page load requirements, or what metadata includes.

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?

One sentence with clear front-loading of the primary action, followed by key behaviors and output format. Every clause contributes information without redundancy.

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 single-optional-param tool, the description covers the core purpose, resizing behavior, and output format. However, it leaves ambiguous whether the screenshot is full-page or viewport, and metadata content is unspecified. No output schema exists, so these gaps are notable but not critical for basic use.

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 already documents maxDimension (optional, default 2000px for Claude API compatibility). The description's 'automatic resizing to fit API limits' adds context connecting the parameter to the tool's behavior, so it adds value beyond the schema.

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 'Take a screenshot of the current page' – a specific verb and resource. It also mentions automatic resizing and output format, which distinguishes it from sibling tools, none of which are screenshot tools.

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 its use case (capturing a visual of the current page) and mentions API limit compatibility, but does not explicitly discuss when to use it versus content extraction tools like chrome_get_content or chrome_get_visible_text, nor does it state exclusions.

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