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

Annotations declare only destructiveHint=true; there is no readOnly guarantee or idempotency info. The description adds the raw endpoint (POST /v3/customer) and the email follow-up, but says nothing about duplicate handling, required permissions, whether locationId defaults to the caller's location, or what happens if the same customer already exists — real gaps for a creating mutation.

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?

Three short sentences, front-loaded with the core action and zero filler. The trailing endpoint string is minor noise but the rest is efficient.

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?

Adequate to call the tool: purpose, entity modes, and the email chaining step are all present, and the schema documents every field with no output schema to explain. Still missing any note on duplicate prevention or what the call returns (e.g., a customer id needed for the follow-up email call), which an agent creating then linking records would want.

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% across all 18 parameters, so the schema carries the semantics; baseline 3 applies. The description's only added value is the person-vs-business framing of customerType, which the schema already documents in its enum description.

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 and clarifies the two entity modes ('a customer (a person) or a fleet account'), which maps onto the customerType enum and distinguishes it from the other create_* siblings. It does not, however, explicitly differentiate itself from update_customer or search_customers beyond the verb.

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 one sequencing instruction — add an email afterwards via shopmonkey_add_customer_email — which is genuinely useful for chaining. It offers no guidance on prerequisites (e.g., checking for duplicates with find_customers_by_email) or when to prefer Fleet over Customer beyond the parenthetical.

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