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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral details: the source truncates facility names to 20 characters, county names are stored as first four letters with spaces removed (e.g., 'NEWY' for New York). It also clarifies the grouping behavior. 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 paragraph of about 100 words. It front-loads the core purpose and examples, then adds parameter guidance. While dense, it could be more structured (e.g., using bullet points for the long list of business types). However, every sentence adds value and there is no fluff.

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?

The tool has 7 parameters (none required) and no output schema. The description adequately explains the function and parameter usage. However, it does not describe the return format or fields when not using `group_by`. With no output schema, the agent would benefit from knowing what fields are returned (e.g., owner name, licence number, dates). This is a notable gap.

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?

Schema documentation covers all 7 parameters (100% coverage). The description adds meaning beyond schema: it provides examples (e.g., ZIP 10034, limit 3, business_type 'inspection station'), explains the 20-character truncation for `name`, the county storage quirk for `county`, and lists the 19 business type codes/phrases. This helps the agent use parameters effectively.

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 it searches a register of 54,563 businesses licensed by NY DMV, listing 14 types (e.g., vehicle inspection stations, repair shops). It gives example queries like "vehicle inspection stations in ZIP 10034" and mentions grouping. This distinguishes it from sibling tools like `ny_dmv_driving_schools` and `ny_dmv_offices`.

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 provides clear context for when to use the tool (searching licensed facilities) and gives example queries. It also explains how to use the `group_by` parameter to get counts instead of a list. However, it does not explicitly state when not to use it or mention alternatives among siblings, which is partially covered by sibling names.

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