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

The description explicitly flags 'MUTATES Autumn billing data', which is consistent with destructiveHint=true and adds useful emphasis for a get-named tool. However, it omits key upsert behavior: whether the supplied name/email/currency are applied when the customer already exists, whether the call is idempotent, and which fields are ignored on the create branch. With only one annotation present, these gaps are material.

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?

Two sentences, with the mutation warning front-loaded before the mechanics and the API endpoint appended for traceability. Efficient, with no filler, though the endpoint path is arguably reference noise rather than selection aid.

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?

The description adds context beyond the schema's parameter docs: it names the API operation (POST /v1/customers.get_or_create) and exposes the create-on-miss behavior, both of which the schema alone does not convey. It doesn't explain what the call returns (existing vs. newly created customer), but with no output schema the absence is a minor gap rather than a blocking one.

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 all nine parameters including the null-able customer_id, expand, and create_in_stripe are already documented in the schema. The description adds only 'by id', which restates the schema; 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 states a specific verb pair and resource ('fetches a customer by id, creating them if they do not exist'), which is precise enough to distinguish an upsert from a pure read. It does not explicitly name autumn_get_customer or autumn_update_customer as the alternatives, so sibling differentiation is implicit rather than stated.

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?

The 'creating them if they do not exist' clause implies the use case (when existence is unknown), but there is no explicit guidance such as 'use autumn_get_customer when you know the customer exists' and no note on what to prefer over autumn_update_customer. Usage is inferable, not stated.

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