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

Goes well beyond the annotations: nothing executes without the human's Passkey, the server re-validates current state on approval and hard-fails on drift, cancel moves zero funds, and the response carries a server-computed economic_effect. Idempotency and conflict behavior (one active request per order+action, same content reuses, changed consequences conflict with the existing id) are exactly the kind of write-safety detail annotations cannot express.

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 scope and submit-only rule are front-loaded, then action-specific bullets, then shared semantics (economic_effect, idempotency) — a logical order with no filler sentences. It is dense but slightly over-compressed in places ("drift hard-fails", "not_received sends nothing back") where a few more words would remove ambiguity.

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 multi-action mutation with no output schema this covers the essentials: gate (Passkey), per-action eligibility, idempotency, conflict handling, and the key response field. It does not describe the refusal payload beyond mentioning order_url, so an agent cannot fully predict the non-happy-path return shape.

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%, so baseline is 3, but the description meaningfully enriches the enums: it attaches a distinct precondition and outcome to each action value and clarifies that reason applies only to request_return, including the special not_received case that "sends nothing back." order_id gains the constraint that it must be one of the caller's own orders.

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 first line states a specific verb and resource ("After-sales ACTION REQUEST on one of YOUR orders") plus the scope token, and the bullets enumerate every supported action with its precondition. An agent can tell this apart from order-placing siblings (webaz_place_order, webaz_pay_order) and from the human-only dispute path without opening any 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?

Preconditions are given per action (delivered + AI-confirm cap for confirm_receipt; Direct Pay unpaid window for cancel; frozen return window and 7-day AI-confirm rule for request_return) and an explicit exclusion is stated ("Disputes/refund handshakes stay human-only for now"). It stops short of naming the sibling tools an agent should reach for in the excluded cases, so routing is inferential rather than explicit.

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