FindBroadband

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds genuinely non-obvious behavior: the verdict is computed server-side and must be presented verbatim, and each alternative's cost_24_months is the true cost over a 24-month window rather than a headline monthly price.

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?

Front-loaded with the usage trigger, then result-handling, then the one non-obvious parameter note. Dense but every sentence carries information; the quote_type sentence is mildly redundant with the schema enum description.

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?

An output schema exists so return values need not be enumerated, and the description still clarifies the cost_24_months semantics and the verbatim-presentation requirement. With annotations covering safety and the schema covering inputs, the remaining gap is minimal; cross-references to get_deal_details and search_addresses are present.

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 every parameter (including quote_type's enum and the uprn/address_label handoff from search_addresses) is already documented in the schema. The description's only parameter guidance, the 'renewal_offer' case for quote_type, largely restates the schema, so the baseline 3 applies.

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: it compares the user's current or quoted price against comparable deals available at their address and returns a computed verdict with 24-month savings. It also names the sibling get_deal_details and how it differs (whole-contract totals), so an agent can distinguish it without opening schemas.

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?

Opens with an explicit trigger ('Use when the user asks whether their CURRENT broadband bill or plan, or a RENEWAL or retention offer...is expensive, competitive or worth switching from') and routes the adjacent case to get_deal_details. It also tells the agent how to act on the result ('present the verdict and figures verbatim rather than deriving your own').

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 readOnly/openWorld/non-destructive, so the safety profile is covered. The description adds real behavior beyond that: the precision field indicates which search variant ran, totals already include intro pricing, post-intro rises and setup fees, and the output must be presented verbatim without re-ranking or recalculation.

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?

Front-loaded with the trigger condition, then workflow, then output rules, then follow-up — a sensible progression. It is long and slightly repetitive ('translate the user's needs into the filter inputs' and 'refine with the filter inputs' restate the same idea), but nearly every sentence carries an operational instruction.

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 9-parameter open-world search with an output schema and annotations already in place, this description covers the full loop: prerequisite, fallback, parameter pairing, output handling constraints, and next-step refinement. Nothing an agent needs before or after the 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 description coverage is 100% and the schema already carries the per-parameter meaning, including the speed-translation examples, so the baseline is 3. The description only marginally extends this with the uprn/address_label pairing instruction and the generic 'translate needs into filter inputs' directive.

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 first sentence states a specific verb (find), resource (broadband deals/offers/packages) and scope (available where they live), and it explicitly names the sibling search_addresses as the upstream step. An agent can distinguish this from check_if_overpaying and get_deal_details 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?

Explicit routing rules: call search_addresses first if no address is picked, fall back to postcode-only when the user declines or no addresses are found, pass address_label alongside uprn once picked. It also prescribes the post-presentation follow-up, so both entry and continuation conditions are covered.

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 cover safety (readOnlyHint, destructiveHint=false), so the bar is lower. The description adds useful behavioral context: results become 'address-precise instead of postcode-wide' when uprn is passed, and clarifies that total_contract_cost is the whole-contract figure over contract_months – a semantic clarification not in the schema. It doesn't discuss rate limits or error behavior, keeping 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 sentences, front-loaded with the when-to-use trigger before the parameter guidance. It is dense but each clause carries information; the only slight redundancy is restating address_label's purpose already in the schema.

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?

Given read-only annotations and an existing output schema (so return shape needn't be explained), the description covers selection (which deal), upstream dependency (deal_id from other tools), parameter intent, and a key field semantic (total_contract_cost). Nothing material for correct invocation 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 description coverage is 100%, so the schema already documents all four parameters thoroughly (including the 'never show this number' note on uprn). The description reinforces intended usage (pass deal_id from earlier result; postcode/uprn/address_label when known; total_contract_cost semantics) but adds little beyond the schema. Baseline 3 applies.

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+resource ('full details for one deal') and explicitly scopes it as 'ONE specific deal already returned by another tool', distinguishing it from siblings find_broadband_deals and check_if_overpaying. It also names the concrete detail fields returned (setup costs, price-rise terms, post-intro behavior, availability).

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 trigger ('Use when the user asks for more detail about ONE specific deal already returned by another tool') and names the upstream tools that supply the deal_id. The distinction from breadth tools is clear via 'already returned by another tool'.

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 only cover the safety profile (readOnly, openWorld, non-destructive). The description adds non-obvious behavioral contract: the response contains a list plus a hidden uprn and display_address, uprn must never be surfaced to the user, the agent must do the matching itself, and the values feed into the next tool. That is meaningful context beyond the structured fields.

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?

It is a single dense paragraph, but it is front-loaded with the usage trigger and nearly every clause carries operational instruction (question phrasing, matching, list fallback, uprn handling). Slightly run-on, but not padded.

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 an output schema present, return values need no explanation, and the description still covers the full usage loop: collection, matching vs. disambiguation, and the handoff of uprn/display_address to downstream tools. An agent has everything needed to call and act on it correctly.

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% for the single postcode parameter, so the baseline is 3. The description nonetheless adds real semantics beyond the schema: house number/name is deliberately NOT a parameter and must be collected in the same question and matched client-side against the returned list, which clarifies how the one-parameter design is meant to be used.

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 gives a specific verb and resource ('find the exact property' for a UK postcode) and clarifies the granularity rationale (broadband availability differs per property). It doesn't explicitly name or contrast the sibling tools (check_if_overpaying, find_broadband_deals, get_deal_details), so it stops short of top-tier sibling differentiation, but the tool's role as the address-lookup entry point is unmistakable.

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 states precisely when to use it (postcode in hand, exact property needed) and gives explicit branching: ask for postcode + house number in ONE question, self-match and proceed when the user already identifies the property, and only render the numbered list when the match is ambiguous or postcode-only. This is a full when/when-not/alternative specification.

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