Create a customer

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

Annotations already disclose readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so mutation semantics are covered. The description adds genuinely new information — the tool refuses live keys — but omits important behaviors such as duplicate-email handling and the consequence of non-idempotency (retries creating duplicate customers).

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?

It is short and front-loaded, and the test-key sentence earns its place. But the brevity reads as under-specification rather than discipline — the body omits essentials for a six-parameter creation tool with a nested metadata object.

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 six params, a nested metadata object, no output schema and no required fields, the description should explain what the created customer response contains, what happens on duplicate email/external_id, and the retry hazard implied by idempotentHint=false. It covers none of this, leaving the caller to guess on a non-idempotent write in an open-world system.

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 only 50%: country, metadata and external_id are documented in the schema, but name, email and locale carry no explanation anywhere. The description compensates for none of this, so an agent gets no guidance on formats, constraints, or that external_id uniqueness can cause rejections.

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 is effectively a restatement of the tool title 'Create a customer' with no additional specificity about scope, resulting object, or differentiation from the many sibling create_* tools (create_subscription, create_invoice, etc.). An agent learns nothing about the tool beyond its name.

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?

'Test keys only: refused with a live key' is an environment constraint rather than usage guidance — it does not say when to create a customer versus calling retrieve_customer/list_customers, nor what prerequisites exist (all six params are optional, and no required field is named). The one useful constraint is stated, but no alternatives or exclusions are given.

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