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

Annotations only supply destructiveHint=true; the description adds the far more useful behavioral detail that Loyverse does not document whether omitted fields survive an update, and converts that into the required workflow of fetching and re-sending the full record. That is exactly the destructive-update risk an agent needs surfaced, plus the underlying endpoint.

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 with zero filler: the create/update distinction comes first, the risky behavior second, the endpoint last. Every clause carries information an agent would otherwise have to guess.

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 an 11-parameter destructive upsert with no output schema, the description covers the highest-risk gap (field loss on update) and the endpoint, which is sufficient to call it correctly. It is slightly thin on what the call returns (created vs updated customer shape) and any auth/rate-limit context, which is minor given the 100% schema coverage.

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 100%, so every one of the 11 parameters is already documented in the schema, including 'id' with 'Omit to create.' The description's mention of `id` therefore does not add meaning beyond the schema, and the remaining fields (address, country_code, customer_code, etc.) receive no extra semantics. 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 resource (loyalty customer) and both verbs (create or update), with the discriminator for the update path stated explicitly ('by passing its `id`'). It also pins the operation to the concrete API surface ('Loyverse: POST /customers'), so an agent can separate it from loyverse_get_customer and loyverse_list_customers without reading any schema.

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 clearly states when the update branch applies and gives an actionable prerequisite ('on update fetch the customer first and send the full record'), which is real when-to-use guidance rather than a restatement. It does not, however, name the sibling to fetch with (loyverse_get_customer) or exclude any misuse case, so it stops short of full routing.

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