Capture Excalidraw canvas

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

With no annotations provided, the description carries the behavioral information burden. It discloses the key operational requirement that the open Browser View must be on the same saved canvas revision, and it explains the dual output behavior (PNG plus diagnostics). It does not discuss errors, side effects, or failure modes, but for a capture/read-style tool the stated precondition covers the most important behavioral constraint.

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 three concise sentences that front-load the primary output, then explain model suitability, then state the required precondition. Every sentence adds useful information and there is no redundant or filler content.

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 that there is no output schema and no annotations, the description does well by naming both return artifacts and the necessary precondition. It is complete enough for an agent to understand what this tool produces and when it can be invoked, though slightly more detail about how clipping diagnostics are structured or when capture fails would make it fully complete.

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 60%, and the schema already documents the critical parameters revision, canvasPath, and projectPath with helpful examples. The description itself adds little parameter-level meaning, and the optional maxWidth and maxHeight parameters are only described by constraints and defaults in the schema. This is adequate but not enhanced by the description.

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 that the tool returns a standard MCP PNG rendered by the open Browser View plus text clipping diagnostics, and explains that image-capable models can use the PNG while other models can use the diagnostics. This is a specific verb-plus-resource description that makes the tool's intent clear, though it does not explicitly name or contrast any sibling tool such as export_canvas.

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 the tool can be used: the View must already be open on the same saved canvas revision. It also gives modality guidance by telling which models benefit from the PNG versus the diagnostics. It does not explicitly state exclusions or alternatives, but the precondition and intended audience are clear.

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