screenshot

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

The description adds meaningful behavioral context beyond the annotations: it discloses that the screenshot is 'resize and compress[ed]' into an 'analysis-friendly PNG' and 'return[ed] directly to the agent.' This explains post-capture processing and delivery mode, which are not evident from the readOnlyHint alone. No contradictions 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, front-loaded sentence that packs capture, processing, and delivery into a clear sequence without superfluous words. Every phrase contributes meaning, making it easy to scan and understand.

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 simple read-only tool with one optional parameter and no output schema, the description is sufficiently complete. It explains the action, the output format (PNG), and that the result is returned to the agent. It does not cover edge cases like device unavailability or permission issues, but given the low complexity and strong schema/annotations, this is not a significant gap.

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 100%, and the schema fully documents the optional 'device_serial' parameter, including examples and fallback behavior. The description adds no parameter-specific information, which is acceptable given the schema's completeness. Baseline 3 applies because the description does not need to compensate.

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's function: 'Capture the current screen, resize and compress it as an analysis-friendly PNG, and return it directly to the agent.' It uses a specific verb ('Capture'), identifies the resource ('current screen'), and describes the output, distinguishing it from sibling tools like dump_ui which inspect UI hierarchy rather than produce a visual image.

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?

Usage timing is implied by the purpose—'Capture the current screen' suggests using it when a visual snapshot is needed—but the description does not explicitly state when to use this tool versus alternatives, nor does it name any alternative such as dump_ui. There is no exclusion guidance, leaving the agent to infer appropriate conditions.

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