get_page_tree

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

With no annotations, the description fully describes behavior: returns a nested tree structure with details on node properties, error behavior ('Figma not connected', timeouts), and prerequisites (Figma bridge and plugin). This covers safety and operational context comprehensively.

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?

Description is concise (a few sentences) with clear sections (Prerequisites, Returns on success, Error behavior, Use this tool). Every sentence adds value, and the main purpose is front-loaded.

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 one parameter, no output schema, and many siblings, the description covers prerequisites, return structure, errors, and usage context. It also references sibling tools for further actions. No gaps remain for correct invocation.

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 coverage is 100% but description adds meaningful context beyond constraints: explains depth values (1=pages only, 2=default frames, 3+ deeper) and performance implications ('Large files at depth 4+ may be slow'). This helps the agent select appropriate values.

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?

Description states a specific verb+resource ('Get the hierarchical node tree of the current Figma file') and adds configurable depth. It clearly distinguishes from sibling tools like capture_screenshot, analyze_design, and get_selection, which serve different purposes.

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 'Use this tool: at the start of a session...' and lists concrete scenarios (understanding file structure, locating frames, finding node IDs, enumerating pages before bulk operations). It also provides depth recommendations. While it doesn't state when not to use it, the guidance is direct and practical.

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