capture_screenshot

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

With no annotations provided, the description carries the full behavioral burden. It states the return format (base64 PNG) but doesn't disclose whether it captures the visible viewport or full page, whether it requires a loaded page, timeouts, or any side effects. The '→ base64 PNG' is useful but insufficient for a tool with zero annotation coverage.

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 extremely short, which is efficient, but it borders on under-specification rather than conciseness. The single sentence conveys the core purpose and return format with zero waste, though it doesn't include behavioral or parameter context.

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 2 parameters, 0% schema coverage, no output schema, and no annotations, the description is critically incomplete. It provides no information about format/quality options, no behavioral context, and no guidance on parameter usage. This is far below the minimum viable for an agent to invoke correctly.

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%, so the description must compensate for the two undocumented parameters (format, quality). It does not mention what format values are valid (e.g., 'png' vs 'jpeg'), what quality range is expected, or defaults for either parameter. The return type is hinted at but the parameters are entirely unexplained.

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 'capture_screenshot() → base64 PNG' clearly states the verb (capture) and resource (screenshot), plus the return format (base64 PNG). It's brief but unambiguous. However, it doesn't differentiate from siblings like page_html or get_markdown, which capture different forms of page content, so it loses a point on sibling differentiation.

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?

There is no guidance on when to use this tool vs alternatives like page_html or get_markdown. No mention of whether it captures the full viewport, current visible area, or requires specific conditions. No when-not-to-use exclusions or alternative tool references are provided.

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