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

Adds real behavioural context beyond the annotations: non-idempotency (two calls = two customers) and the auto-numbering rule when customerNumber is omitted. The annotations already flag destructiveHint=true, so what's left unsaid is a lesser gap — e.g. no mention of permissions or validation failures (duplicate orgNumber).

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, zero filler, with the primary action first and the risk warning front-loaded before the dedup advice. Every sentence earns its place.

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?

No output schema exists, yet the description never indicates what comes back (e.g. the created customer ID), which would be useful for chaining into bokio_create_invoice_draft. Otherwise it covers purpose, side effects and a safe pre-check, which is adequate for a create 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 only 50% across 10 parameters (one nested object), so the description should compensate more. It does add genuine semantics for customerNumber (omitted → Bokio assigns next number), but says nothing about required name/type or the enum choices.

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 ("Create a customer") plus the tenant scope ("the company's Bokio"), which cleanly separates it from bokio_list_customers and bokio_get_customer. An agent can route to it 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?

Explicitly names the alternative ("check bokio_list_customers first") and the condition that should trigger it, given the non-idempotent behaviour. That is exactly the when-to-use/when-to-use-something-else guidance an agent needs.

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