Find the right token for an intent

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

Annotations declare the tool is read-only, and the description adds meaningful behavioral detail beyond that: it returns resolved values per theme and explains token selection with reasoning about neighboring tokens. This gives the agent a clear picture of the tool's output without contradicting any annotations.

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, both substantive: the first explains the tool's function and output, the second gives practical usage guidance. No filler or repetition of the title.

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?

For a simple, read-only tool with only one required parameter and no output schema, the description covers the key context: how to phrase the input, what kind of results to expect, and when to prefer this tool over guessing. It could be slightly more complete by explicitly noting the optional limit parameter or naming a sibling alternative, but these are minor gaps.

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 description explains the intent parameter semantically ('Describe what you are styling in plain words') and the schema provides useful examples for intent. However, the optional 'limit' parameter is not mentioned in the description and has no schema description, so the semantics of that parameter are left entirely to inference from its name and min/max constraints.

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 uses a specific verb ('Describe... and get') with a clear resource ('semantic tokens') and states what is returned: resolved values per theme and a rationale comparing to neighboring tokens. This clearly distinguishes the tool from siblings like get_tokens or search, which retrieve tokens rather than recommend them from a natural-language intent.

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 instruction 'Use this instead of guessing a token name or reaching for a hex value' gives clear guidance on when this tool is appropriate. It does not explicitly name alternative sibling tools or state when not to use it, but the intended use case is unambiguous.

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