Photograph part of the frame

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

Beyond the readOnlyHint/destructiveHint annotations, the description discloses meaningful behavior: it captures the back buffer rather than the screen, includes interface elements and dust, and only returns a path once the PNG bytes are complete. It also warns about the file-existence race condition, which is valuable operational context.

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 front-loaded with the core purpose and organized into clear sections for arguments and behavior. It is somewhat verbose, especially the final paragraph's phrasing, but the extra detail is substantive and not wasted.

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 three parameters and an output schema, the description covers the purpose, parameter semantics, capture source, edge-case behavior, and timeout handling. Nothing needed to call the tool correctly appears to be missing.

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 coverage is 0%, and the description fully compensates by explaining every parameter. It enumerates valid region values and their rationale, clarifies that target addresses a specific client, and gives precise semantics for timeout as a single budget for the whole call including the PNG write.

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 region of the game's back buffer and returns a PNG path, which is specific and actionable. It distinguishes the capture source from the screen and from the in-game capture camera, but it does not explicitly differentiate this from sibling tools like captures or read_capture.

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 gives useful context for when the tool is appropriate, such as reading the game's rendered output rather than the screen, and explains why the region parameter is required. However, it does not explicitly name alternatives among the sibling tools or state when not to use this tool, leaving tool-selection guidance largely implicit.

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