figma_changes

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

Annotations only declare readOnlyHint/openWorldHint; the description goes well beyond them, disclosing that results are a single-snapshot edit view that shows nothing deleted and never reveals what an edit was, only when. It also explains rolling-up semantics, undated-node handling, shared limit behavior across pages, and count-scoping rules for page/exclude_pages.

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?

Purpose is front-loaded, but the definition is one dense block of unusually long clauses mixing result-field semantics, counting rules, and repeated pointers to 'the server's instructions (figma-reader help)' that appear three times. Almost every sentence carries information, yet the packing makes key constraints hard to extract.

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?

With no output schema, the description carries the output burden and largely does so, naming lastEditedAt, editedNodes, created, page, path, pathIds, undatedNodes, byPage, and excludedPages. Residual gaps remain around exact shapes of byPage/pathIds entries, but an agent has enough to call it and interpret results.

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 real meaning: the returned 'since' is the instant the value was read as, exclude_pages defaults to the project's excludePages and is echoed as excludedPages, and the limit is shared across pages so one page cannot crowd out others. It also clarifies page/path/pathIds interplay beyond the schema's text.

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?

Opens with a specific verb+resource+scope: 'Top-level layers created or edited since a date or duration, from Figma's edit times per node.' It then defines what a top-level layer is and explicitly distinguishes itself from the sibling figma_diff ('figma_diff lists removals'). An agent can tell this apart from figma_search or figma_get_tree 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?

States its operating context clearly (edit metadata from one snapshot, since a date/duration) and routes deletions to figma_diff. It does not, however, state when to prefer it over options like figma_search or figma_diff for non-removal history, so the when-not side is only partially covered.

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