open_canvas

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

With no annotations, the description must carry behavioral disclosure, and it does flag the key trait: the call can create a canvas as a side effect. It does not say whether an existing canvas is reset or preserved, whether creation requires a title, or what a successful switch returns, leaving meaningful gaps for a mutating operation.

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?

Two short sentences, zero waste. The core action is front-loaded and the creation side effect is stated immediately after, before the parameter hint.

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 two-parameter, non-nested tool with no output schema, this covers the essentials: what it does, that it may create, and where ids come from. The remaining gap is behavioral detail on existing-canvas handling, which is minor given the tool's simplicity.

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%, so the schema already documents both parameters and the baseline is 3. The description adds a small amount of meaning by clarifying that the id parameter accepts either a canvas id or a project name, but says nothing about how title behaves beyond the schema's 'when creating.'

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?

Specific verb and resource: 'Switch the browser to a named canvas,' plus the important side effect '(creates it if needed).' It references the sibling list_canvases as the source of ids, but does not distinguish this tool from read_canvas or clear_canvas, which also operate on a 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?

It gives a concrete sourcing path ('an id from list_canvases') and accepts a project name as an alternative, which is genuinely helpful. It never states when to choose this over read_canvas or clear_canvas, nor what happens if the canvas already exists, so the guidance is implied rather than explicit.

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