override_risk_policy

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

With no annotations, the description carries full burden and does so impressively. It discloses atomicity, one-time scope, audit logging of the required reason, and idempotent retry behavior (same override, no secondary). These are critical behavioral traits beyond the basic schema.

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?

Four concise sentences, each delivering essential information with no redundancy. The first sentence carries the core purpose, followed by constraints, side effects, and idempotency.

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?

The description covers purpose, scope, constraints, audit trail, and idempotency. Given no output schema and moderate complexity, it is mostly complete, but lacks return value or error behavior details which could be inferred from the tool's nature.

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 coverage is only 17% (expires_at only), so the description must compensate. It adds meaning for reason (required, audit-logged) and idempotency_key (retries bind to same override), but leaves account_id and request_id semantics unexplained, creating a partial gap.

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 clearly states the tool creates a one-time, atomic risk policy exception for the next order, allowing override of user-defined caps only. This distinguishes it from siblings like set_risk_policy (persistent policy) and place_order (execution).

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?

It explicitly says it only allows overriding user-defined caps for a single order and never bypasses basic accuracy checks, making the intended use case clear. It doesn't name alternatives but the sibling context implies set_risk_policy for persistent changes, so the guidance is nearly complete.

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