The pages, and which one is open

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

The description goes beyond annotations by disclosing that opening a page moves the designer's view, changes nothing in the file, has nothing to undo, and is not gated by the Edits switch. These are meaningful behavioral details that an agent cannot infer from readOnlyHint or destructiveHint alone.

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 two actions are front-loaded in a compact, scannable format, and the second paragraph earns its place by explaining when and why the tool matters. No sentences are wasted.

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-action navigation tool, the description covers both operations, parameter selection, the side effect of moving the designer's view, and the relationship to sibling tools. There is no output schema, but list's return meaning is stated clearly enough for an agent to use the tool correctly.

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?

All three parameters are already fully documented in the input schema, so the baseline is 3. The description adds only a light restatement of the 'by pageId or by name' routing, which does not provide meaning beyond the schema.

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 states a specific verb and resource for each action: list returns every page and the current one, open switches to a page by pageId or name. This makes it easy to distinguish from the sibling reading tools, which are all page- or node-focused.

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 explicitly says to call this before concluding something is missing, because every other reading tool only answers about the current page. It also contrasts open with figma_select and explains that it is not behind the Edits switch, giving clear when-to-use and when-not-to-use context.

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