Scan all text

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

Annotations already declare readOnly/destructive/openWorld, so safety is covered. The description adds real behavior beyond them: pagination by item, that a truncated scan announces truncation rather than silently returning a partial document, and that the result carries a `scope` naming the scanned root (with the Slides edge case). Missing only rate/size caveats and auth notes.

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?

Front-loaded with the purpose, then scope of holders, then pagination, then result shape, then the alternative. It is dense and clause-heavy, but each sentence adds a distinct fact; no filler.

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?

With no output schema, the description still discloses the key return behaviors (per-item pagination, truncation signaling, `scope` field) and the default nodeId resolution. Adequate for a read-only scan tool; only finer detail on result item shape is absent.

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%, so the schema already documents all five parameters (limit, types, cursor, nodeId default chain, session). The description only adds that `types` narrows the result set and that table cells yield one item each — useful but marginal over the schema. Baseline 3 is appropriate.

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?

States a specific verb (scan) and resource (text in a subtree with full characters), and enumerates exactly which holders qualify (TEXT, sticky/shape/connector text, code blocks, table cells). It explicitly distinguishes itself from figma_search_nodes (single-text lookup) and figma_get_design_context (maxTextChars fallback), so an agent can route without opening a schema.

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?

Concrete use cases are named (copy audit, translation extract, recovering text truncated by figma_get_design_context), and the alternative is given with its trigger condition: 'Finding one text: figma_search_nodes { text }.' When-to-use and the sibling selection condition are both explicit.

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