memoire

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

With no annotations provided, the description carries full burden and does so effectively. It discloses key behavioral traits: error handling ('Never throws — returns an empty object {} if no tokens are in the registry'), transformation rules ('Token keys are derived from the last segment of the token name, lowercased and hyphenated'), output filtering ('Empty token categories are omitted'), and value preferences ('CSS variables are preferred over raw values when available'). No contradictions with annotations since none exist.

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?

Perfectly structured with zero wasted sentences. Each paragraph serves a distinct purpose: transformation process, prerequisites, return format, error behavior, and sibling differentiation. Information is front-loaded with the core purpose immediately clear.

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?

Given the tool's complexity (transformation logic, error handling, sibling differentiation) and lack of both annotations and output schema, the description provides complete context. It thoroughly explains what the tool does, when to use it, how it behaves, what it returns, and how it differs from alternatives—covering all necessary aspects for an AI agent to correctly invoke it.

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?

The tool has 0 parameters with 100% schema description coverage, so the baseline would be 3. However, the description explicitly states 'No parameters required' contextually by explaining the tool operates on existing registry data, adding meaningful context about why no inputs are needed. This elevates the score above baseline.

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 clearly states the specific action ('Map design system tokens') and target resource ('Tailwind config theme extension object'), distinguishing it from siblings like get_tokens (which returns raw token data) and pull_design_system (which fetches tokens from Figma). It explicitly defines the transformation process from registry tokens to Tailwind-ready format.

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 states when to use this tool vs alternatives: 'Use this tool vs get_tokens: get_tokens returns raw token data for inspection; sync_design_tokens returns a Tailwind-ready patch you can directly paste into your config.' Also provides prerequisites ('Tokens must already be in the local registry') and exclusions ('Tokens of type "other" are skipped').

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