desktop-touch-mcp

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

With no annotations provided, the description carries the full burden and does so effectively. It discloses key behavioral traits: it uses the left mouse button only, does not support right-drag or middle-drag, includes safety guards with lensId (identity stable, foreground, coordinates in rect), and provides post-perception state feedback. This covers operational constraints and safety features beyond basic functionality.

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 appropriately sized and front-loaded, starting with the core action and use cases, then detailing optional parameters and caveats. Every sentence adds value, such as explaining lensId functionality and button limitations, with no redundant or wasted words.

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 complexity (9 parameters, no output schema, no annotations), the description is largely complete: it covers purpose, usage, behavioral traits, and parameter semantics. However, it could be slightly enhanced by mentioning error handling or typical response formats, though the lack of output schema makes this less critical. It adequately supports tool selection and invocation.

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 56% (5 out of 9 parameters have descriptions in the schema). The description adds meaningful context beyond the schema: it explains that windowTitle 'optionally focuses before drag' and lensId 'run safety guards... before dragging and receive post.perception state feedback without a screenshot.' This clarifies the purpose and interaction of these parameters, compensating for the moderate coverage gap.

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 explicitly states the tool's function with a specific verb ('Click and drag') and resource ('from (startX, startY) to (endX, endY)'), and distinguishes it from siblings by specifying it's for 'sliders, drag-and-drop, canvas drawing, and window resizing'—unlike mouse_click or mouse_move. It clearly articulates what the tool does beyond just the name.

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 clear context for when to use this tool (e.g., 'for sliders, drag-and-drop, canvas drawing, and window resizing') and mentions optional parameters like windowTitle and lensId for specific scenarios. However, it does not explicitly state when not to use it or name alternatives among siblings, such as mouse_click for simple clicks or scroll for scrolling actions.

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