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

Annotations already declare destructiveHint/idempotentHint, so the safety profile is covered. The description adds real value beyond them: PATCH-style partial update semantics (only passed fields change) and the fact that bank-detail-dependent settings (direct debit) cannot be set here. It stops short of saying what makes the call destructive or how invalid ids behave.

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?

Front-loaded with the operation class and packed into two short clauses with no filler. The trailing "customer.update." tag is opaque jargon but costs almost nothing.

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?

A 23-parameter mutation with no output schema and thin schema descriptions needs more than two clauses. Missing are the required-id contract, conditional field dependencies, and what an agent should expect on failure; the description alone would not let an agent call this correctly.

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 only 39% across 23 parameters, so the description should compensate and it does not. It says nothing about customer_id being required, the conditional rules (organization required for business, last_name for consumer) or the payment_type/days_for_payment interaction, leaving the undocumented half unaddressed.

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?

"WRITE: update fields of an existing customer" gives a specific verb, resource and operation class, and the patch clause ("only the fields you pass change") separates it cleanly from fastbill_create_customer and fastbill_get_customer. An agent can pick this tool without opening the 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?

The WRITE prefix implies when to use it, and "Bank details are not accepted by this tool" sets one scoping exclusion. But there is no guidance on prerequisites (e.g. reading current values via fastbill_get_customer first) or on when to prefer create vs update.

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