vision_capture

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

With no annotations, the description carries the burden, and it does disclose the live-image-then-preview fallback and that returned MCP resources must be re-read for current state. It does not mention side effects (update_timeline defaults true) or the cost/latency of forcing a fresh capture.

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?

Three short sentences, front-loaded with the core action and followed by source fallback and re-read guidance. No filler, though the re-read sentence is slightly tangential.

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?

An output schema exists so return values need not be explained, but a 6-parameter tool with zero schema documentation and no annotations leaves the agent unable to interpret the configurable grid/label/timeline options.

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% across 6 parameters, so the description must compensate, yet it says nothing about grid_px, show_labels, show_centers, show_layer_bounds, or update_timeline. Only session_id and the canvas-pixel source are implied.

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 and resource: forcing a fresh AI vision frame from GIMP canvas pixels, with a documented source preference (live image, then session preview). This clearly separates it from render/preview siblings, though it never names them.

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 an implied trigger ("whenever the AI wants to visually review progress") and a source preference, but there is no explicit when-not to use it or comparison against the sibling preview_render / export_image tools.

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