Find the right token for an intent

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

Annotations already mark this as read-only (readOnlyHint=true), so safety is established. The description adds behavioral context beyond annotations by describing the output: 'resolved values per theme and a note on why that token rather than a neighbour.' It does not explain limit behavior or edge cases, but for a read-only suggestion tool, this is adequate.

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 description is two concise sentences, front-loading the main action ('Describe what you are styling') and adding a clear usage tip ('Use this instead of...'). No unnecessary words or repetition.

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?

While the description covers the core purpose and gives some output details (resolved values per theme, reasoning), it fails to explain the 'limit' parameter and does not clarify how themes are determined or whether the tool relies on the current theme. Given there is no output schema, more detail on return values and parameter behavior would be needed to be fully complete.

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 'intent' parameter is well explained in both the schema (with examples) and the description ('Describe what you are styling'). However, the 'limit' parameter has no description in either the schema or the tool description, so its purpose (likely output count) is unclear. With schema description coverage at 50%, the description only partially compensates for the missing documentation.

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 tool's function: 'Describe what you are styling in plain words and get the semantic tokens that apply.' It uses a specific verb (get) and resource (semantic tokens), and distinguishes itself from sibling tools like 'get_tokens' by emphasizing intent-based natural language input and reasoning about token selection.

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?

The description gives clear context: 'Use this instead of guessing a token name or reaching for a hex value.' This indicates when to use the tool (when you don't know the exact token) but does not explicitly name alternative tools or describe when not to use it beyond the 'instead of' guidance. It gives useful context without full exclusions.

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