figma_generate_changelog

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

No annotations, so the description carries the burden and does well: it discloses the extra API lookback call (a cost trait agents should know), that it delegates to figma_diff_versions and figma_get_file_versions, and that it returns both a markdown string and structured diff data. It doesn't state permissions or anything about large-diff behavior, keeping it below a 5.

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?

Four sentences, zero waste, with purpose leading and the return shape, cost, and cross-tool semantics following in order of importance. Nothing is repeated that structured fields already provide verbatim.

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 correctly fills the gap by naming the two return payloads (markdown string plus structured diff). With no annotations, it implies a read-only generation step and discloses the extra call. Only missing is guidance on failure modes or very large diffs, which is minor for a read tool.

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 cross-tool semantics: 'Same component_ids and mode semantics as figma_diff_versions' tells the agent the parameter meanings are shared and can be reasoned about once. The 'current'/HEAD guidance partially duplicates the schema.

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+scope: 'Generate a human-readable markdown changelog between two versions.' It immediately distinguishes itself from figma_diff_versions by disclosing that it wraps that tool and enriches the result, so an agent can tell the two apart without opening schemas.

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 frames itself as an enrichment layer over figma_diff_versions at the cost of 'one extra cheap API call,' which implicitly tells the agent when to prefer it. It also gives the concrete usage hint "Use 'current' for to_version to changelog against HEAD." It stops short of an explicit 'use X instead when you don't need markdown' exclusion.

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