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

Annotations already declare non-read-only, non-destructive, non-idempotent; the description adds real value on top by warning that FastBill performs no duplicate detection and that bank/direct-debit data cannot be supplied here. It does not say what is returned on success (no output schema exists), which is the one notable behavioral gap.

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?

Four dense clauses, front-loaded with the WRITE marker and the required field, then preconditions, then the failure mode, then the endpoint. No filler or repetition.

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 22-parameter mutation with open-world and no output schema, the description covers the highest-risk facts: required type branching, duplicate risk, and the excluded bank-detail path. What it omits is the response shape (e.g., whether the new customer ID comes back) and permission/error behavior.

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 only 41% across 22 parameters, so the description could compensate more. It does clarify the conditional requirement among customer_type/organization/last_name and the bank-details exclusion tied to payment_type 6, but most of the remaining ~18 fields get no meaning beyond their names and length limits in the schema.

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 precise verb and resource ("WRITE: create a customer") and grounds it with the underlying API call ("customer.create"). The create verb itself separates it from fastbill_update_customer and fastbill_get_customer, though no explicit contrast is drawn.

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 concrete preconditions (customer_type required; organization for business, last_name for consumer), a when-not (bank details are not accepted here, set them in FastBill), and an alternative tool with its condition (search with fastbill_list_customers first because duplicates are not checked). No guidance on routing an existing customer to update_customer.

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