editor_input

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

Beyond the annotations, it discloses single-use capture IDs with a 120s expiry, that coordinates are in the returned preview image rather than the original PNG, that only ONE action is sent per call, the scroll sign convention, and foreground/rect/unobscured requirements. That is rich operational context an agent cannot infer elsewhere.

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?

Front-loaded with the core action and result, then constraints and coordinate system in dense, waste-free sentences. Every sentence earns its place.

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 12-parameter mutation tool with no output schema, the description covers the workflow, safety prerequisites, and return value well. It is still thin on failure behavior and the semantics of several input parameters.

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 0%, so the description must carry the load. It usefully explains x/y (preview pixels, not original PNG), delta sign, and captureId expiry, but leaves key chord syntax, text vs. literal Unicode handling, button, holdMs, clickCount and toX/toY for drag undocumented.

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?

States a specific verb (send ONE click, key chord, text, scroll or drag) and resource (the window), and clarifies the one-action-per-call scope plus that it returns a new screenshot. No sibling tool provides input synthesis, so the distinction is unambiguous.

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?

Gives clear preconditions: a fresh captureId, target foreground, unchanged rect/title, unobscured click point, and verifying the fresh image. It implies the capture_editor_window workflow but does not explicitly name alternatives or when not to use it.

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