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

Annotations only cover the generic readOnly/destructive/openWorld profile; the description adds substantial behavior the agent could not infer: an exact-name duplicate check that aborts the call, default-filled unspecified settings, a per-call confirmation default that can be disabled, an explicit warning that the action reaches other people, and the API-key permission requirement.

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 core purpose and dedup/return-value facts are front-loaded and every clause carries information. The confirmation requirement is stated twice in slightly different words ('By default you confirm each call; you can switch that off' and 'Reaches other people: confirm with the user before each call'), which is mild redundancy but arguably reinforces an important safety point.

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 correctly discloses the return value (customer_id) and its intended consumer. Combined with the dedup behavior, permission requirement, and confirmation warning, an agent has everything needed to call this correctly for a simple 2-parameter creation tool.

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 coverage is 100% and both properties already carry descriptions, so the schema does the heavy lifting. The description restates that a name and billing email are supplied but adds no format, validation, or default-value detail beyond the schema; baseline 3 applies.

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 names a specific verb and resource (create a customer) and immediately scopes it to the two fields it takes (name, billing email). It also distinguishes itself from the sibling acumatica_list_customers by describing the dedup check and from acumatica_create_ar_invoice by naming it as the downstream consumer of customer_id.

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?

It gives clear context for when this tool matters: the returned customer_id feeds create_ar_invoice, and the duplicate check means you don't need to pre-verify the name. It does not state explicit exclusions (e.g., use list_customers to look up an existing customer instead of creating one), so it stops short of full when/when-not guidance.

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