figma_load_file

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

Annotation Contradiction: annotations mark readOnlyHint=true, but the description explicitly says 'Export (Save local copy)' and describes caching and re-exporting, which are state-writing behaviors. The description adds useful staleness context (exportedAt, fileModifiedAt, refreshIgnored), but the read-only signal is directly contradicted.

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?

The text is dense but well organized: purpose, caching/performance, and date semantics each get a distinct passage. It is longer than strictly needed for two parameters and repeats the export/cache idea, but every sentence carries real operational guidance.

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 snapshot/load tool with no output schema, the description covers the return summary, cache reuse, large-file latency, refresh behavior, and the fileModifiedAt staleness caveat. There is enough for an agent to call it correctly and interpret its results without inspecting siblings or schemas.

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?

Even though schema coverage is 100%, the description adds substantial meaning: node-id handling in URLs, the local '<name> [<key>].fig' fallback from FIGMA_FILES_DIRS, the distinction between live export and disk read, and refreshIgnored behavior. An agent gains much more than the bare schema would provide.

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?

The description names a specific action and resource: 'Export (Save local copy) and decode a Figma file' and lists the returned summary (pages, node counts, variable collections, styles, components). It also separates this tool from the many sibling tools by presenting it as the cached snapshot source: 'Snapshots are cached; other tools reuse them.'

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 explains when to use a cached result versus refreshing ('pass refresh to export it again'), and gives a clear when-not for paths ('Has no effect when file is a path to a .fig ... pass the key or URL'). The note that other tools reuse the snapshots implies this is the intended entry-point loader.

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