firestarter_shipping_options

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

Annotation Contradiction: the annotation declares readOnlyHint=true, yet the description says 'Pass refresh: true to re-fetch live carrier rates and persist them before showing the menu.' Persisting data is a write side effect, contradicting the read-only claim. Even though the rest of the description gives useful preview/no-purchase clarification, the contradiction forces a score of 1.

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 description is dense and front-loaded, but it has slight redundancy, such as 'preview before paying' and later 'Does NOT select or pay — it's a preview' and twice describing the returned. It is still a well-structured, useful text; just a bit longer than strictly necessary.

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 tool with no output schema, the description thoroughly explains the return value (numbered Delivery Options menu), how to advance from a menu number to firestarter_approve, when to use select_index, refresh for live rates, and the two main sibling alternatives. It covers all the important contextual decisions an agent would face.

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?

The input schema already has 100% coverage with meaningful descriptions for all parameters. The description adds value beyond that by explicitly connecting the numbered menu to firestarter_approve's shipping_option_index, clarifying why select_index is used for a preview, and noting that refresh may be used when the quote appears stale. This goes farther than simply restating the 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 states a specific verb ('Show and compare'), a specific resource ('delivery speeds for an order awaiting approval'), and a precise preview action ('preview the re-priced total for a chosen speed'). It also explains the output contract (numbered menu, shipping_option_index) and differentiates it from firestarter_execute and firestarter_shipping_estimate, so the agent can distinguish it from siblings.

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?

The description gives explicit when-to-use guidance: use for delivery speed/cost questions, faster delivery wishes, or speed/price trade-off questions. It also gives exclusions and alternatives: firestarter_execute already lists options inline, approving without a pick uses the cheapest rate, and firestarter_shipping_estimate is for listings without execution.

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