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

Annotations already declare destructiveHint and idempotentHint, but the description adds genuinely new behavior: line-level cascade, irreversibility by any other tool, the claimed Last Price credential, and the 403 refusal for self-registered sandbox keys. This is exactly the context annotations cannot carry.

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 short sentences, front-loaded with the action and cascade, then preconditions, then prerequisites. Every sentence carries distinct information; no filler.

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 single-parameter mutation with no output schema, the definition covers state preconditions, cascade scope, irreversibility, and both auth gates. An agent has everything needed to call it correctly or route around it.

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% with a single required uuid parameter already documented as coming from list_orders. The description's 'pass order_id' repeats the schema without adding format or sourcing detail beyond it, so baseline 3 applies.

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 ('Delete an order') and immediately discloses the cascade ('and its lines'), which distinguishes it from the sibling update_order. An agent can tell exactly what this tool removes without opening the 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?

Explicitly bounds when the tool works ('Only a draft or cancelled order can be deleted') and names the remedy when it doesn't ('cancel it first otherwise'). It also states the credential and workspace prerequisites, leaving nothing to inference.

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