Style part of a text

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and the description does not contradict them. It adds real behavioral context beyond the annotations: 'Everything is checked before the text changes' (atomic validation), the single-colour-source constraint, and environment verification status. It stops short of describing failure modes or the returned result, but the additions are substantive.

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?

Dense but front-loaded: scope first, then selection mechanics, then design-system binding, then the colour-source exclusivity caveat, then the sibling pointer and environment note. Every sentence carries information an agent needs; 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?

For a 24-parameter mutation tool with no output schema and only 71% schema coverage, this description supplies the critical selection semantics, variable-binding guidance, colour-source constraint and pre-write validation. The gaps (error/return behavior, a few undocumented scalar params) are minor given the annotations and sibling pointer, so it is close to but not fully complete.

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 24 parameters and 71% schema coverage, the description compensates well: it explains that paragraph spacing, paragraph indent, list and indent widen to the whole paragraphs the part touches — a non-obvious behavioral rule absent from the schema — plus the exclusivity of color/fillStyle/colorVariable and the 'node:<id>' link form. It does not cover every remaining undocumented parameter (weight, fontSize, case, decoration), so it falls short of a 5.

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?

Names a precise verb+resource ('Style part of one text node') and enumerates the concrete use cases (bold word, coloured price, underlined link, bulleted paragraph). It explicitly distinguishes itself from the sibling figma_set_text_properties, which handles whole-node properties, so an agent can route between them without opening either 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?

Gives clear context: it names the alternative tool for whole-node properties (alignment, resizing, truncation) and states the selection rule (match/occurrence vs start/end). It also flags the editor support matrix (Design; unverified: FigJam, Slides). No explicit 'when not to use' beyond the single sibling pointer, so not quite a 5.

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