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

Annotations already flag readOnlyHint=false, destructiveHint=true and idempotentHint=true; the description adds the non-obvious patch behavior (unsent fields are untouched) and a consent-integrity rule. It does not spell out what destructiveHint means here (overwriting existing field values) or the failure mode for a bad id, so it stops short of full disclosure.

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 WRITE marker and the field list, ending with the endpoint. Every clause carries information (mutation type, patch semantics, consent rule, route) 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 7-parameter mutation with no output schema, the description covers what changes, what is preserved, the consent guardrail, and the route. Missing are the response shape and error behavior for an invalid customer_id, which matters somewhat given destructiveHint=true and openWorldHint=true.

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%, so the baseline is 3, but the description maps plain-language field names onto the schema's keys — notably "phone" to contact and "newsletter consent" to marketing_subscribed — which resolves a real naming mismatch an agent would otherwise guess at.

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 WRITE verb and resource ("change a customer's ..."), then enumerates the mutable fields and names the endpoint POST /v1/customers/{id}. That is enough for an agent to separate it from shoprocket_create_customer and shoprocket_get_customer without opening 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?

"Only the fields you pass are sent" establishes partial-update semantics, which is the key calling convention, and the marketing_subscribed caveat tells the agent not to blanket-set consent. It stops short of naming when to prefer create vs update or what happens on an unknown customer id, so no explicit alternatives/exclusions.

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