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

Annotations already declare readOnlyHint=false, destructiveHint=false, and openWorldHint=true, so the safety profile is partly given. The description adds genuinely useful non-annotation context: it returns a customer_id, it does not deduplicate by name, the customer is not notified, it mutates accounting data, and it needs a Cotlet API key. Deduction for the confusing back-to-back 'It reaches nobody' / 'Reaches other people' phrasings, which muddy the external-impact message.

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?

The core guidance (create, returns id, search first) is front-loaded and earns its place. However, the confirmation requirement is restated repeatedly ('it asks for your OK', 'you confirm each call', 'confirm with the user before each call'), and the 'reaches nobody / reaches other people' pair reads as self-contradictory boilerplate that dilutes the message.

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 mutation tool with no output schema, the description covers the essentials: what it returns (customer_id), the duplicate-check gap, the auth requirement (API key), and the confirmation obligation. Nothing critical is missing, though the duplicated confirmation language slightly weakens clarity.

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 three parameters (name, type enum, email) are already documented in the schema. The description adds nothing about parameter format or semantics beyond what the schema provides, which is the expected baseline when the schema does the heavy lifting.

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 company or individual customer') plus the data consequence (changes your accounting data). It distinguishes itself from siblings by naming create_customer_invoice as the downstream consumer and list_customers as the search alternative, so an agent can route correctly without opening either 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 tells the agent to 'Search with list_customers first, because this call does not check for a customer with the same name' — a named alternative plus the exact condition that selects it. It also states the confirmation requirement before each call, leaving nothing to inference.

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