figma-mcp-go

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

Annotations cover destructiveness and read-only status. Description adds scope context ('entire collection' implies breadth of deletion) but fails to disclose behavioral implications of idempotentHint=false or what happens to nodes bound to deleted variables.

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 sentences, zero waste. Front-loaded with the destructive action, followed immediately by parameter constraints. Every word earns its place.

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?

Adequate for the complexity given rich schema and annotations, but gaps remain around return values (no output schema), error conditions (what if both IDs provided?), and side effects on bound variables.

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 has 100% coverage establishing baseline of 3. Description adds critical semantic constraint 'either...or' which clarifies the logical requirement that one parameter must be provided despite schema marking both as optional, preventing invalid empty calls.

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?

Clear verb (Delete) and specific resources (variable/variable collection). Distinguishes from sibling tools like delete_nodes or delete_style by specifying 'variable' domain, though lacks explicit comparison to similar deletion tools.

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?

Provides mechanical guidance ('Provide either variableId or collectionId') implying XOR logic, but lacks strategic guidance on when to delete a single variable vs an entire collection, or prerequisites like checking for bound nodes.

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