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

Beyond the annotations, it discloses the real side effects (money returned the same way it was paid, stock restocked, Odoo sale order and delivery touched) and the execution model ('Simulated first; one approval runs every step'), which tells the agent this is a staged proposal rather than an immediate irreversible mutation. That reconciles with destructiveHint=false since nothing executes without approval.

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 tight sentences with no filler: scope first, exclusion and alternative second, execution model third, context last. Every sentence adds decision-relevant information.

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?

With an output schema present, return values need no explanation, and the description covers side effects, approval, and scope well. The remaining gap is the undocumented optional parameters (accounts, reason, notification), which an agent must infer from the schema alone.

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 only 33% across 9 parameters, so the description needs to carry more weight than it does. It alludes to refund and restock behavior but never states that 'refund' and 'restock' are flags, nor explains reason, note, notify_customer, erp_account, shop_account, or account; six of nine parameters are left to the bare schema.

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 opens with a specific verb and resource ('Propose cancelling a web shop order') and enumerates exactly what is affected: the shop (refund + restock) and the company system (Odoo sale order and open delivery). It is clearly separable from sibling tools like returns_create_awb and refund_issue, which it explicitly routes shipped orders to.

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 states the primary condition (unshipped orders) and the explicit exclusion with alternatives: 'Shipped orders cannot be cancelled: use returns_create_awb then refund_issue.' It also flags the operating context ('Works on: Support desk') and the approval flow, so an agent knows both when to call it and what happens next.

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