firestarter_assist_quote

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

Annotations provide minimal signal (readOnlyHint: false, destructiveHint: false), leaving the description to carry the burden — and it delivers. It discloses the non-destructive nature ('books nothing, charges nothing'), surfaces a real-world quirk (Lalamove in Thailand requiring coordinates), describes the return ordering ('cheapest-first'), and warns about the downstream consequence (quoting is not booking; booking is a real charge requiring human confirmation). No contradiction with annotations.

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?

Dense but every sentence earns its place — purpose, when-to-use, safety, parameter guidance, and downstream warning. It is front-loaded with the core purpose. The one structural demerit is that it's a wall of six sentences in a single paragraph; breaking the safety and Lalamove notes into separate lines would improve scannability, but there is no fluff.

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 high-complexity tool (11 params, no output schema), the description covers the essentials: when to fire, safety profile, location-pin handling, return format (cheapest-first, quote_ref), and the critical warning that booking is a real charge requiring user confirmation. It could add error-case behavior or how quotes can fail (e.g., no couriers in area), but nothing an agent needs to invoke it correctly is obviously missing.

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 schema coverage at 55%, the description meaningfully compensates for the undocumented lat/lng parameters: 'Include lat/lng for both stops when the user shared a location pin — some couriers cannot quote without coordinates.' It also maps the domain ('courier crew,' 'bulky') to the bulky/two_person params. It doesn't explicitly address needs_disassembly or declared_value_cents, but the parameter guidance it adds goes well beyond 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?

States a specific verb+resource ('Get pickup+delivery quotes') with a clear scope ('for a PHYSICAL item... weight racks, sofas, appliances'). It achieves differentiation from siblings like firestarter_shipping_estimate and firestarter_assist_book by describing exactly what this tool does and what it hands off (quote_ref → assist_book).

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 explicit when-to-use triggers: 'Use when a buyer or seller asks how to move an item, or proactively when an item is clearly bulky.' The 'Pure price check: books nothing, charges nothing' implicitly distinguishes it from the booking sibling firestarter_assist_book, and the warning that booking 'requires the human's prior confirmation' sets a condition for the follow-up action. It could name an alternative tool to rule out (e.g., shipping_estimate), but the context is clear.

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