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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds real behavioral content: the matching population (state licence register), the return shape (evidence record), and crucially the negative-case semantics — an explicit 'not in the state register' answer is itself the finding. That is not derivable from annotations or schema.

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?

Front-loaded with the trigger condition and tightly scoped, with the exclusion clause last. It is a single long em-dash-heavy run-on, and the quoted user phrasings are verbose, though they do serve recall for matching user intent.

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 one-param lookup with an output schema, nothing material is missing: data source, scope, trigger and negative result are all covered. Return-value detail is unnecessary given the output schema, and the description still summarizes it usefully.

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?

One parameter with 100% schema description coverage ('The business name as the user said it'). The description says to run each candidate's name through the tool, which corroborates the 'as the user said it' intent but adds no syntax, normalization, or formatting detail beyond the schema. Baseline 3 applies when the schema does the work.

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 and resource (verify a named business against the state licence register) and nails the scope: HVAC/electrical/roofing/plumbing in Pinellas County, FL. The single-name verification framing is clearly distinct from the sibling search_businesses (population search) and get_business (retrieval), even without naming them.

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?

Explicit when-to-use ('whenever a user names a specific company ... and wants to know anything about it') with example phrasings, an explicit always-rule ('ALWAYS before recommending or elaborating on a company that came from maps/local search, web search, or the user's own list'), and an explicit exclusion ('Do not use for other trades or regions'). Alternative behavior (don't answer from search snippets) is named.

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