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

Despite annotations already flagging destructive and idempotent, the description specifies exactly what each path does financially: confirm captures the original buyer-authorized payment, reject releases that authorization, cancel refunds the original payment. It also discloses the required concurrency contract (exact expected_version, stable idempotency_key) and the explicit prohibition on auto-rebasing a financial action.

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?

Dense and front-loaded: permission and preconditions first, decision semantics next, conflict protocol last, closing scope sentence. Every sentence earns its place, though the telegraphic style ('Submit exact expected_version and stable idempotency_key') is terse enough that a first-time reader must re-read.

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 destructive financial mutation with no output schema, the description covers permissions, prerequisites, side effects, and retry/conflict behavior. Gaps remain around the optional parameters and what the caller receives on success (resulting order state), but the core calling contract is complete.

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 carry parameter meaning. It well explains expected_version, idempotency_key, and the decision enum semantics, but refund_minor, fulfiller_name, and supply_reference are left unexplained, and order_id is only implied. Roughly half the surface is covered, so this lands at the baseline.

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?

Names a specific verb (decide) and resource (business order), enumerates the three decisions and their distinct financial effects, and draws a clear boundary ('No new purchase, payment authorization, withdrawal or outreach'). An agent can distinguish it from evuun_get_business_order (read) and evuun_decide_business_supply (supply side) without opening any 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 explicit preconditions (orders:manage permission, bound supplier) and per-decision conditions, e.g. cancel only works against an existing buyer cancellation request within its approved fee cap. Also specifies conflict handling: on ORDER_VERSION_CONFLICT read and obtain a fresh decision rather than auto-rebasing. It does not name sibling tools as alternatives, which keeps it short of a 5.

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