memoire

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

With no annotations provided, the description carries the full burden and delivers comprehensive behavioral information. It details prerequisites (Figma bridge running, plugin connected), error behaviors ('Throws "Figma not connected"', 'Returns a bridge error'), and the specific return format (image content block with type, data, mimeType). It also explains the tool's role in workflows like the self-heal loop.

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 efficiently structured with clear sections (purpose, prerequisites, returns, error behavior, usage guidance). Every sentence adds value: the first sentence states the core function, followed by essential operational details, output format, error handling, and specific use cases. There is no redundant or wasted text.

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 tool with 3 parameters, 100% schema coverage, but no annotations or output schema, the description provides exceptional completeness. It covers prerequisites, error conditions, return format (compensating for lack of output schema), and integration with sibling tools. The guidance on when to use SVG vs PNG and scale settings adds practical context that the schema alone doesn't provide.

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 baseline is 3. The description adds meaningful context beyond the schema: it explains that omitting nodeId captures the entire page (implied but not explicit in schema), provides workflow context for obtaining node IDs, and gives practical guidance on format selection (SVG for vector components, PNG for complex frames) and scale usage (1 for quick inspection, 2-3 for high-quality analysis).

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 the specific action ('capture a screenshot'), the resource ('Figma node or entire current page'), and the output format ('returned as image data'). It distinguishes this tool from siblings like analyze_design (which analyzes images) and get_selection/get_page_tree (which provide node IDs).

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?

Explicit guidance is provided on when to use this tool ('to visually inspect a component or frame before/after mutations', 'first step in the self-heal loop', 'to feed a node image into analyze_design'), when not to use it (requires prerequisites), and alternatives (prefer SVG for vector components, PNG for complex frames). It also references sibling tools like check_bridge_health for verification.

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