Verify Business

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

The description richly discloses side effects and behaviors beyond annotations: credit deductions (1/15/25 credits), refund policy for unanswered calls, authentication requirement, and the deep-tier fallback to a quick result when unavailable. It also clarifies that a no-match still deducts credits. These are not conveyed by the annotations (readOnlyHint=false, openWorldHint=true, etc.) and add critical operational detail.

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 dense but every sentence earns its place. It opens with the core purpose, then moves through usage constraints, tier options, limitations, auth, and credit policy. There is no fluff; the paragraph flows logically and front-loads the most critical information. Given the complexity of the tool (credits, tiers, refunds), the length is appropriate.

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 description fully covers the tool's ground: purpose, when to use, tier details, jurisdiction subset, auth, and credit/refund policies. It even describes return content for quick ('existence + status + good standing') and deep ('entity type, formation date...') despite the lack of an output schema. The guidance against search_entities positions it well among siblings.

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?

Although the schema already covers 100% of parameters, the description adds meaningful semantics to key ones: it explains 'level' tiers with credit costs, mentions 'force_refresh' as adding 10 credits (deep only), and implies jurisdiction handling via 'subset of jurisdictions'. It also relates entity_name to the need to ask for a name. Some parameters (webhook_url, entity_type) rely solely on schema, but overall the description significantly augments parameter understanding.

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+resource: 'Confirm a specific, named business in one jurisdiction' and explicitly lists use cases ('verify, check, confirm, or look up a company's existence, status, good standing'). It clearly distinguishes this tool from search_entities, stating 'do NOT fall back to search_entities', and positions it as 'the PRIMARY tool' for verification intent.

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 gives explicit when-to-use guidance: 'the PRIMARY tool whenever the user wants to verify...' and instructs to ask for a company name if missing. It also names the alternative tool to avoid: 'do NOT fall back to search_entities'. It further specifies tier availability ('Deep is available in a subset of jurisdictions') and authentication requirements, leaving no ambiguity about usage context.

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