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

Annotations already declare write/idempotent/destructive/openWorld=false, so the description's real contribution is the data-fate disclosure: id, name, business and language come back, while email, phone, tax id and address are stored but never returned — a genuinely useful insight an agent cannot infer from the schema. It does not explain the destructiveHint=true implication (e.g. whether a created customer can be undone or removed), which is the one 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?

Three tight sentences: when to use, what comes back and what does not, then the exclusion. The routing constraint is front-loaded and no sentence is filler.

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 9-parameter create tool with nested address, an enum, an output schema and full schema coverage, the description covers purpose, exclusion and the notable non-returned fields — enough to call it correctly. It stops short of addressing reversibility/cleanup or the idempotent retry path in prose, though both are partly covered elsewhere.

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 the baseline is 3, but the description adds meaning beyond the schema by telling the agent which supplied fields are persisted-but-not-echoed versus returned, which affects how it should report results back to the user. It adds nothing about businessId, legalEntity or requestId retry semantics, but those are already well documented 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 specific verb and resource ('add a new customer to a business') plus a concrete use case (a client about to be invoiced). It also distinguishes itself from the sibling update_customer with 'Not for changing an existing customer', 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?

Gives an explicit trigger ('when someone asks to add a new customer'), a motivating example, and an explicit exclusion ('Not for changing an existing customer') that clearly points at update_customer among the siblings. Both the when and the when-not are stated.

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