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

Annotations already declare readOnlyHint and openWorldHint, so the description's role is lighter. It adds valuable behavioral context: what the return contains (attributes plus universal serviceMode options), the refinement flow, and the conditional skip behavior. This is more than annotations alone provide, though not exhaustive (e.g., no error cases).

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 compact yet information-dense, with a clear front-loaded statement of purpose followed by actionable usage guidance and return summary. Every sentence earns its place; no filler or repetition of schema fields.

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 one simple parameter, no output schema, and strong annotations, the description covers all necessary aspects: when to call, what it returns, how to handle the refinementAvailable flag. It is complete for an agent to invoke the tool correctly in a conversation flow.

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 input schema provides 100% coverage of the single parameter, with a detailed enum and clear guidance on how to pick the value. The description itself adds little beyond 'specific subcategory', but because the schema fully handles meaning, the baseline of 3 is appropriate.

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 starts with a specific verb ('List'), a clear resource ('refinement dimensions'), and a scope ('for a specific subcategory'). It distinguishes this tool from siblings by explicitly mentioning search_businesses and the 'before' relationship, making the purpose unmistakable.

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 explicit when-to-use guidance: 'Call this BEFORE search_businesses when the user's request is broad', with concrete examples. It also specifies the interaction pattern (politely ask whether to narrow, offer all results option) and the conditional fallback ('If refinementAvailable is false, skip refinement and go directly to search_businesses'). This is exemplary guidance.

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