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

Annotations only supply destructiveHint=true; the description adds the substantive behavioral risk that Loyverse does not document whether omitted fields survive an update, implying omitted fields may be wiped, and prescribes the safe workflow. That is real operational disclosure beyond the annotation, consistent with destructiveHint. It stays at 4 because nothing is said about return values, idempotency, or auth needs.

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 tight sentences with the create/update scope and the data-loss warning front-loaded, then the operational instruction. The trailing 'Loyverse: POST /customers.' endpoint note is marginally extraneous for an agent but costs little.

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 mutation tool with destructiveHint=true, no output schema, and full schema coverage, the description covers everything an agent needs to call it safely: mode selection, required name, and the fetch-then-send-full-record rule. Return-value detail is unnecessary given parameter documentation.

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 all 11 parameters carry their own descriptions, including `id` ('Existing customer id to update. Omit to create.'). The description restates the create-vs-update role of `id` but adds no format, constraint, or field-level meaning beyond the schema, so the 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?

States specific verbs and resource ('Create a loyalty customer, or update one by passing its `id`') and immediately pairs the create/update duality with the discriminator parameter. This clearly separates it from read/list siblings like loyverse_get_customer and loyverse_list_customers, and scopes it to 'customer' versus the upsert_category/upsert_supplier siblings.

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 explicit mode selection ('Omit to create' / pass `id` to update) and a concrete prerequisite workflow: fetch the customer first and resend the full record on update. It does not name the alternative tool (loyverse_get_customer) explicitly nor state when not to use this tool, so it stops short of the top band.

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