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

Annotations already declare a non-read-only, open-world, non-idempotent write, and the description adds the crucial context: no charge happens in the conversation, customer service verifies by phone before sending payment details, and the item is not locked before payment. It does not address what happens on duplicate submissions or failures, which keeps it from a 5.

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?

Three short sentences with the gating condition front-loaded, followed by payment behavior and the alternative route. No filler, no repetition of the title.

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?

Core workflow semantics for a mutating, open-world tool are well covered, including the return value (order number) despite no output schema. However, an agent still lacks guidance on dry_run, payment-method selection, and what to do about retries given the non-idempotent annotation, which is incomplete for a 9-parameter write tool.

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?

With only 22% schema description coverage across 9 parameters, the description must compensate, and it partially does: it explains the semantic gate behind customer_confirmed (phone consent) and implies product_id must reference a priced, on-sale item. But dry_run, pay_method, wechat, name, note and city remain unexplained in the description beyond the thin schema text, leaving several inputs opaque.

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 action (submitting an order intent for a priced, on-sale piece), the exact preconditions (explizit buy intent plus phone consent with customer_confirmed=true), and the output (order number). An agent can distinguish it from handoff_to_human and get_order_status 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?

Gives an explicit trigger condition (customer has clearly chosen a priced item and agreed to share a phone number) and an explicit exclusion with the named alternative: '客人想讲价就改用 handoff_to_human'. Both when-to-use and when-not-to-use are covered.

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