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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds substantial behavior: a non-London postcode returns needs_a_call immediately, unanswered questions are returned in order, and unpricable homes return a reason plus contact route. It also states that it neither places an order nor contacts the customer, which is exactly the kind of consequence detail annotations cannot convey.

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 purpose and geography are front-loaded, then the flow, then the return shapes, then the safety boundary. Almost every sentence carries distinct information, though the iterative-call rule is stated twice in slightly different words, which could be tightened.

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?

There is no output schema, so the description carries the full burden of explaining returns, and it does: questions with options, itemised per-option prices, extras, available installation dates, needs_a_call, and the reason/contact route when unpricable. Nothing essential for a stateful, multi-round pricing call is 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?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning: answers must reuse the question ids and option values returned by earlier calls, and postcode is explicitly optional and irrelevant to price. That explains the stateful contract of the 'answers' object beyond what the schema says.

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 ('Work out Renzy's fixed, fully fitted price for a new gas boiler or air conditioning') and bounds it geographically to Greater London. It is clearly a pricing/quotation tool, distinct from siblings such as order_installation or book_plumber.

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 gives precise calling instructions: pass the product plus every answer so far, omit answers to start, and re-call after each round because questions depend on prior answers. It implicitly separates itself from ordering ('it does not place an order'), but it never names order_installation or check_availability as the alternative to use instead, so explicit routing is missing.

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