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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds substantive behavior beyond them: it caps results at five candidates, clarifies that the similarity score is not an underwriting confidence, and defines the needsClarification signal plus the required handling. That is real operational context, not restatement.

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?

Four sentences, each carrying distinct load: invocation timing, input constraint, return shape, and edge-case handling. The most important guidance (use first) is front-loaded, and there is no filler.

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?

With no output schema, the description responsibly describes the return payload (up to five candidate code sets with a similarity score and needsClarification). The only gap is that the optional state parameter is never characterized, which matters because the schema explicitly warns it is the operating state rather than the user's location.

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 description coverage is 100%, so both parameters are already documented in the schema (including the same 'bakery'/'HVAC contractor' example). The description adds a filtering instruction ('leave out the business name, city and other details') that goes slightly beyond the schema, but it never mentions the state parameter, so it does not fully enrich parameter meaning.

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?

States a specific verb+resource (find a business's insurance classification) and explicitly positions itself relative to siblings: 'Use this first ... before suggesting coverages or estimating premiums.' An agent can distinguish it from suggest_coverages, explain_coverage, and get_carrier_recommendations without opening any schema.

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?

Gives explicit when-to-use ('first, when the user describes what their business does'), states the downstream tools it precedes, tells the agent what to include versus exclude in the input, and prescribes the fallback action when needsClarification is true ('ask the user which activity fits instead of choosing one').

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