Set text

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

Goes well past the annotations: it discloses that the current font is loaded first (so foreign text works), that mixed-style nodes are flattened with only the first character's style retained, and that the result carries flattened.runs so the segments can be reapplied. That is exactly the kind of lossy-mutation detail the annotations (destructiveHint=false, idempotentHint=true) do not convey.

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 core action and scope, then the behavioral caveat about style flattening. The heavy parenthetical nesting makes it dense, but every clause (font loading, style loss, editors) carries real operational value.

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 mutation tool with no output schema, it covers target node types, editor support, font handling, and the risky style-flattening side effect and its recovery path. The main omission is any indication of the response shape or confirmation behavior after a successful set.

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 50%: session and idempotencyKey are self-documented in the schema, while nodeId and content have no schema descriptions. The description explains what 'content' semantically replaces and that a node is targeted, but adds no nodeId format or identification guidance, so it only partially compensates for the gap.

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 ('Replace the content') and resource (TEXT node), then enumerates the additional node kinds it covers (sticky, shape/connector label, code block) and names the sibling to use for tables (figma_edit_table). An agent can distinguish it from figma_create_text and figma_set_text_range 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?

It routes the agent to alternatives for tables (figma_edit_table) and for restyling after flattening (figma_set_text_range), and states supported editors (Design; unverified FigJam/Slides). It stops short of an explicit when-to-use statement against figma_set_text_properties or figma_find_replace_text, so it is clear context rather than full when/when-not guidance.

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