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

Annotations already establish read-only, non-destructive, closed-world behavior. On top of that, the description adds useful behavioral context: shelves carry 'live guide counts,' and data is delivered 'as machine-readable data rather than prose,' which informs the agent about freshness and output format. No contradiction with 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?

The description is a single front-loaded sentence that leads with the action and then lists the vocabulary contents. It is slightly dense due to the enumerations and parentheticals, but there is little wasted wording.

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 parameterless, read-only tool with an output schema and annotations covering safety, the description is complete: it names every category the taxonomy includes and notes the live-count behavior. Nothing return-related is needed because an output schema exists.

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 zero parameters, so there is nothing for the description to document. Per the baseline for parameterless tools, the description's content is sufficient without adding parameter-level detail.

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 opens with a specific verb and object — 'Get the bicycle.guide vocabulary' — and enumerates the categories it returns: domains, shelves, series, personas, guide_types, and classification conventions. This clearly differentiates it from siblings like list_guides or get_guide, which would return actual guides rather than the taxonomy.

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 makes the data domain clear, so an agent can infer this tool is for vocabulary/classification lookups rather than guide content. However, it never explicitly states when to use it over list_guides, get_guide, or list_capabilities, nor does it provide exclusions or alternative routing.

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