kill_switch

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

With no annotations, the description carries the full burden and does disclose the two facts that matter most: the action is destructive (cancels resting orders) and irreversible for agents (cannot be switched off). It omits the blast radius — whether it is account-wide or global — and whether open positions or fills are affected.

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?

Two sentences, front-loaded with the effect and followed by the constraint. Every clause adds information and nothing is padded.

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?

An output schema exists, so return values need no explanation, and the core effect and irreversibility are covered. For an irreversible destructive halt with no annotations, however, the description leaves out scope, human override, and what exactly 'resting ones' covers.

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 needs to explain the single required 'reason' parameter, and it says nothing about it. The name is largely self-explanatory, which prevents a 1, but there is no guidance on format, whether it is logged, or why it is required for an already-irreversible action.

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 uses a specific verb plus resource and scope: 'Stop all new orders and cancel resting ones.' That clearly separates it from the single-order sibling cancel_order and from submit_order, even though no sibling is named explicitly.

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?

'Agents can turn it on, never off' is a strong implicit warning that this is a last-resort action, which guides usage. But it never states the conditions that should trigger it versus cancel_order for a single order, nor any prerequisite such as approval_status or policy_limits checks.

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