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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=true, openWorldHint=true), so the description's real value is the disclosure that the tool does NOT email the customer and the explicit consent constraint on marketing_subscribed. That is a genuine side-effect disclosure beyond what annotations provide. A note about what happens if the email already exists would push this higher.

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 the operation type front-loaded as "WRITE:" and no filler. Every clause carries a distinct piece of information.

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?

Covers side effects and consent, but with no output schema the description never says what a successful call returns (e.g. a customer ID) or how duplicate emails are handled, which matters for a non-idempotent create. Adequate but leaves meaningful gaps for a 6-parameter write tool.

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 parameter already carries a description. The description's only parameter commentary repeats the schema's own wording for marketing_subscribed ("true only if the customer opted in"), adding no new meaning. 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 a specific verb and resource ("add a customer record") and labels it WRITE up front, so an agent can distinguish it from read siblings like shoprocket_get_customer or shoprocket_list_customers. It never names the sibling it supersedes or what to do on duplicate emails, which is where update_customer would come in.

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?

Implies usage via the WRITE marker and the consent caveat, but gives no explicit when-to-use guidance such as "use this instead of update_customer when the customer does not exist yet" or any prerequisite about duplicate emails. The agent has to infer the routing itself.

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