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

Annotations only declare readOnlyHint=true; the description adds substantial behavioral context beyond that — the {tooLarge, children} overflow response with instructions to read children one by one, the token requirement ('Needs a Figma token on the site'), image URL rendering, and the raw flag. This is exactly the extra operational detail annotations cannot carry.

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?

Information is front-loaded with the primary return shape before the mode branches, and every sentence carries operational weight. It is dense and slightly run-on in the middle, but there is little waste.

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 complex tool with no output schema, the description compensates by describing the return tree, the overflow object, and the auth prerequisite. An agent has everything needed to make a correct first call without a dedicated output schema.

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 baseline is 3, but the description adds meaning: imageIds produces rendered URLs 'as upload-media sourceUrl for raster photos' and raw yields 'the unprocessed node,' which go beyond the terse schema text. The nodeId/fileKey semantics largely restate the schema, keeping it 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?

States a specific verb+resource outcome: 'A Figma node as build-ready data: a clean HTML/CSS-in-JSON tree (tags, text, inlined icon svg, computed styles, resolved flex/grid).' It also disambiguates two distinct behaviors (node read vs file outline), so an agent can tell exactly what it will get. No sibling competes for Figma reading, and the scope is unmistakable.

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?

Explicitly routes between modes: 'Without nodeId: the file outline ... to pick the frame to read,' and names the prerequisite 'get-skill-doc {id:"site-assets-contract"} — read it before the first call.' It also explains when to use imageIds and raw, leaving little to inference.

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