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

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds concrete behavior the annotations cannot express: cancelling all resting orders, reduce-only position closes across exchanges, blocking new positions, and human-only resume with a verification code. The permission note about third-party apps is genuinely useful context not captured by any structured field.

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?

The critical scope and emergency framing are front-loaded, and each sentence carries useful information (when to use, resume restriction, sibling exclusion, next step). The 'Input: reason' clause is redundant with the schema and could be trimmed, but the overall structure is efficient and easy to scan.

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 single-parameter destructive tool with an output schema and rich annotations, the description covers everything an agent needs: intent, scope, alternatives, permission model, and a follow-up confirmation step. Return values need not be explained because an output schema exists.

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 100% and the single 'reason' parameter is already documented as 'Why, for the user and the audit log'. The description's 'Input: reason' merely repeats this without adding format, length, or defaulting guidance. Baseline 3 is appropriate because the schema does the semantic work.

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 ('Emergency stop for the whole account') and spells out scope: cancel every resting order, close every position on every exchange with reduce-only orders, and block new positions. It explicitly distinguishes itself from the sibling close_position for single-position closes, so an agent can select it 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 explicit when-to-use criteria ('only when the person asks to stop everything or something is clearly wrong') and a when-not alternative ('Not for closing one position (use close_position)'). It also states the resume path, so the agent knows the action is not self-reversible.

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