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

Annotations already carry destructiveHint=true and idempotentHint=true, so the description adds crucial nuance beyond those flags: soft-delete to bin (reversible deletion), transactional all-or-nothing semantics, and two precise failure prerequisites (unknown ids, linked non-deleted invoices). This is exactly the behavioral context annotations cannot express, particularly the distinction between a soft-delete and a permanent delete.

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 sentences with zero filler: the core operation and soft-delete behavior are front-loaded, followed by failure semantics, then body format and the alternative tool. Every sentence earns its place by adding information neither the schema nor the annotations contain.

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 one-parameter bulk operation with annotations covering the safety profile, the description covers the operation, transactionality, failure modes, body shape, and the alternative tool. There is no output schema so the success response is unspecified, and the interaction between idempotentHint and retrying an already-binned client is left unresolved — minor gaps in an otherwise complete definition.

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 0%, so the description must compensate. It shows the exact body shape '{clients: [{id} ...]}' and clarifies that the single parameter is a list of customer IDs. It could add detail on id format or duplicate handling, but the structure is sufficiently specified for a correct call.

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?

The description states a specific verb and resource: 'Delete multiple customers in one transaction,' which clearly differentiates it from the single-customer sibling delete_client. Adding 'soft-delete to bin' further specifies the operation's nature and scope. An agent can immediately identify what this tool does and how it differs from nearby alternatives.

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 description explicitly routes to the alternative: 'For a single customer use delete_client.' It also provides strong when-not-to-use guidance via the all-or-nothing failure conditions — the request fails if any id is unknown or any customer has linked non-deleted invoices — telling the agent which scenarios make this tool unsuitable. The resource term 'customers' also cleanly separates it from delete_suppliers_bulk.

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