Get design context

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

Annotations already establish the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the lower bar applies. The description nonetheless adds real operational context: truncation with truncated:true plus nextCursor to resume, maxNodes/maxTextChars/table-cell cutoffs, and that includeCss is slower. However the calibration for read-only annotated tools topped out at 3 when return-format and pagination behavior were absent; here truncation is covered but the description remains a payload inventory rather than disclosing limits such as rate, file-size, or permission requirements. A 3 is the honest landing point.

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 imperative warning is front-loaded and virtually every clause carries distinct facts about scope, payload, or truncation. The cost is readability: a single unbroken paragraph of semicolon-separated inventories makes it hard to scan for one specific behavior, so it falls short of a 5.

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 14-parameter tool with no output schema, the description effectively serves as the return contract, enumerating node fields, token/component use lists, FigJam and Slides specifics, and the scope flag. Combined with truncation and cursor semantics, an agent has everything needed to call it correctly without further reference.

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?

With 100% schema description coverage the baseline is 3, but the description earns an extra point by explaining cross-parameter behavior the schema cannot: maxNodes produces truncated:true and nextCursor, and cursor is "the nextCursor of a truncated call, unchanged," which is the resumption contract. It does not add meaning for depth, absolute, session, or the include* toggles beyond what the schema already says.

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 precise verb+resource and enumerates the exact payload (per-node geometry, auto-layout, fills/strokes/effects/radius, styled text runs, styles and variables by name, FigJam/Slides structures), so an agent knows exactly what it will get. It never explicitly disambiguates from the many overlapping read siblings (figma_get_node, figma_get_nodes_info, figma_get_metadata), so it stops short of a 5.

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?

"READ THIS BEFORE YOU BUILD OR CODE" is a clear, front-loaded directive on when to reach for this tool. It also explains default scope resolution (selection → page → focused slide) which tells the agent what it will get without arguments. It names no alternative or when-not condition, so no 5.

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