Renzy Plumbers

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

Goes well beyond the annotations: it discloses third-party data sharing (name, phone, address, problem description sent to Renzy), the downstream human follow-up (Renzy phones to confirm), the absence of payment collection, and the non-idempotent side effect with a 'do not retry a call that succeeded' warning. This is exactly the context 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?

Five tight sentences, front-loaded with the action and immediately followed by the prerequisite, the human confirmation step, the data-sharing disclosure and the retry warning. No sentence is redundant.

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 6-required-parameter write tool with no output schema, the description covers the call contract, side effects and misuse risk thoroughly. The only gap is that it never says what a successful call returns (e.g. a booking reference), which matters since there is no output schema to fall back on.

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 description coverage is 100%, so each of the 8 parameters is already documented. The description adds only the provenance of slot_id (from check_availability) and the confirmation of the address/rate, which the schema largely covers; the baseline 3 is appropriate.

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 and resource ('Book a Renzy plumber') plus the scope constraint ('one arrival window') and the destination ('the customer's address'). It is clearly distinguishable from siblings check_availability, quote_installation and order_installation.

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 prerequisite and the correct sequencing ('Call check_availability first and use a slot_id it returned') and an explicit pre-call obligation ('Confirm the window, the hourly rate and the address with the customer before calling this'). It also names the retry exclusion, which is the main misuse risk.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description's 'read-only, does not change anything' largely reinforces structured data. It still adds real context the annotations cannot express: that coverage may fail for a given postcode, and that results include arrival windows plus hourly rates in GBP for a bounded N-day horizon.

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?

Two sentences, front-loaded with the core capability, followed immediately by the usage rule and the read-only guarantee. No filler and nothing buried at the end.

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?

With only two simple parameters, full schema coverage, and rich annotations, the definition is complete. Even though no output schema exists, the description explains what comes back — a coverage determination and bookable windows with hourly rates — which is exactly what an agent needs to plan the following book_plumber call.

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 description coverage is 100%, so both the postcode format and the 1–21 day range are already documented in the schema. The description only restates 'postcode' and 'next N days' in prose, adding no formatting, defaulting, or edge-case detail beyond what is already structured.

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 and resource — checking postcode coverage and listing bookable arrival windows with hourly GBP rates over N days — and pairs it with a clear negative scope ('it does not book a visit'). An agent can distinguish this from book_plumber, quote_installation, and order_installation 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?

It gives an explicit sequencing rule, 'Use this before book_plumber,' which is the primary dependency an agent needs. It does not address when an agent should skip this check in favour of quote_installation or order_installation, so the routing guidance is clear but not exhaustive.

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

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

Annotations already flag a non-idempotent, open-world, destructive write; the description adds non-obvious context on top: customer PII is transmitted to Renzy, a quote email is sent, no card is collected or charged, the response carries a photo-upload link, and duplicate calls create duplicate orders. That last point directly explains the idempotentHint=false constraint in operational terms.

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 critical constraints are front-loaded (what it does, what to confirm first) and the caveats follow in short declarative sentences. Slightly long for a simple order primitive, but every sentence conveys a constraint an agent could otherwise get wrong.

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 13-parameter, nested-object mutation with no output schema, it covers the important ground: data sent, email side effect, no payment, duplicate-order hazard, and one return element. It leaves the rest of the response shape (order id, total, status) and failure handling unspecified.

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 provenance meaning: answers come from the priced quote result, package_id is the chosen option, install_date must be one of the quoted dates, and extras are among what gets confirmed with the customer. It stops short of explaining formats for address fields or what the answers object must contain.

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 and resource ('Order a fixed-price installation') and scopes it by origin ('priced by quote_installation') and by the date source ('on one of its installation dates'), which cleanly separates it from quote_installation (pricing) and book_plumber (a different trade).

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 a clear prerequisite ('priced by quote_installation') and a pre-call confirmation ritual covering option, extras, total, date and address, plus an explicit do-not-retry rule. It never explicitly names when to prefer book_plumber or check_availability, so routing against those siblings is left implicit.

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

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.