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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description reinforces them with the concrete consequence: retrying creates a duplicate. It adds genuinely non-structured traits — the required API key scope, the fact that the store's 'new customer' webhook fires, and that balance/credit limit/loyalty points must be set elsewhere.

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?

Five compact sentences, each doing distinct work: write class, excluded fields, auth, idempotency hazard, side effect, and endpoint. The risk warning is front-loaded after the purpose statement, with no filler.

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 15-parameter mutation with side effects and no output schema, the description covers auth, idempotency, webhook firing, and field exclusions well. The one real gap is the return value — with no output schema, the agent isn't told what comes back (e.g., the new customer ID) to chain into a follow-up call.

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 each of the 15 fields carries its own description, so the schema carries the parameter burden. The description's only parameter-adjacent content is a negative statement (balance, credit limit, loyalty points cannot be set), which is useful scoping but doesn't add syntax, defaults, or format semantics beyond the schema.

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?

Opens with an explicit verb class ("WRITE: create") plus a concrete resource ("a customer in the store"), which separates it cleanly from the read-side siblings like phppos_get_customer and phppos_list_customers. It also bounds the scope by naming fields that are out of reach here, so the agent's mental model of the tool matches what it does.

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?

Gives a concrete precondition ("check phppos_list_customers first") tied to a specific failure mode, and states the auth requirement (Read/Write API key). It stops short of explicitly routing create-vs-update decisions to phppos_update_customer, so the alternative-selection guidance is strong but not complete.

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