screenshot_capture

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

With no annotations, the description must carry the full behavioral burden; it does disclose the write side effect and that output goes to a temp file or an output path. However it says nothing about screen-recording permissions, overwrite behavior, or where the returned file reference comes from, and the text is truncated mid-sentence about the output destination.

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 visible sentence is front-loaded with the core action and has no filler, which is good. But the text is cut off mid-clause, so the structure cannot be fully evaluated and the reader is left without the complete output-path explanation.

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 at minimum say how the target and destination are chosen and whether permissions are needed. It gestures at the PNG destination but is truncated and omits prerequisites, leaving the agent with only a partial picture.

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 tool takes zero parameters, so there is nothing for the description to disambiguate beyond the implicit defaults; the baseline of 4 applies. The mention of 'display, window, or region' hints at selection modes that are not actually exposed as inputs, which is mildly confusing but not harmful.

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 names a specific verb (captures) and resource (a single frame of a display, window, or region) plus the artifact produced (a PNG file), which clearly separates it from screen_record_start and web_screenshot. It stops short of explicitly contrasting with those siblings, but the scope is unmistakable.

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 statement of when to use this tool rather than screen_record_start or web_screenshot, nor any prerequisite context. The agent must infer from the name alone that this is for one-off still captures.

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