textual_screenshot

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

The annotations already declare readOnlyHint=true and destructiveHint=false, so the description's lack of explicit safety disclosure is acceptable. The description adds context that the screenshot is 'visual' and of the 'running app', which is helpful, but does not mention potential performance impact or resolution limitations. No contradiction with annotations.

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 a single, well-front-loaded sentence with no unnecessary words. It efficiently conveys the core purpose and key format options.

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?

Given the tool has a required session_id parameter and an optional format parameter, the description is incomplete. It fails to explain what session_id refers to or how to obtain it, and does not list accepted format values. The output schema exists but the description omits any behavioral details like whether the output is a file path or base64 data.

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?

With 0% schema description coverage, the description must compensate for documenting parameters. It only hints at the format parameter by mentioning 'text or SVG', but does not explain session_id or specify allowed format values. The default value and the role of session_id remain undocumented, offering minimal added 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 it captures a visual screenshot of the running app, and mentions the text or SVG format options. It is specific about the resource (running app) and verb (capture), but does not explicitly differentiate from the sibling tool 'textual_snapshot', which may have overlapping functionality.

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 no guidance on when to use this tool versus alternatives like textual_snapshot or textual_query. It does not specify when to choose text vs SVG format, nor any prerequisites for using the tool.

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