export_tokens

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

With no annotations supplied, the description carries the full burden and covers the important behavior: only the first mode of each collection is exported, cross-variable references become aliases, and the return-vs-write fork is spelled out. It omits whether existing files in outputDir are overwritten and whether local file access requires plugin permissions, which matters for a tool that writes to disk.

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?

Two dense sentences, zero filler, with the output formats and the collection/mode constraint front-loaded before the outputDir branch. The parenthetical is used efficiently to hold the alias-resolution caveat.

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 single optional-parameter tool with no output schema and no annotations, it sufficiently covers what is produced and where it goes, including that response contents are returned when outputDir is absent. Only the exact shape of that in-response payload and overwrite behavior remain unstated.

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% and the sole outputDir parameter is documented there as the folder for tokens.json and tokens.css, created as needed. The description adds the meaningful negative case (no outputDir means contents come back in the response), but adds no formatting or path semantics beyond the schema, so baseline 3 is right.

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 (exports) and resource (local Figma variables) plus the exact output artifacts: DTCG JSON and CSS custom properties. The mention of alias resolution and per-collection first mode makes it distinguishable from the read-only get_variables sibling 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?

Explicitly branches on the presence of outputDir: omit it to get file contents in the response, supply it to write tokens.json and tokens.css to disk. That is clear situational guidance for the one decision the caller must make, though it never names get_variables as the alternative for reading raw variable data.

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