Fast Fibre: fiber internet check

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds genuinely useful behavior beyond that: it is free with no sign-up, it never quotes prices online (a specialist gives them on the call), and it enumerates what the response contains. That pricing constraint in particular prevents an agent from making an unsupported promise.

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 core purpose is front-loaded in the first sentence, and the remaining sentences each carry distinct information (service identity, cost/sign-up terms, return contents, pricing policy). It is slightly dense with business detail but no sentence is wasted.

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 no output schema present, the description compensates by enumerating the return contents (status, human-readable summary, available speeds, callback eligibility). Combined with fully documented parameters and the pricing/no-sign-up rules, an agent has everything needed to call it and interpret the result.

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 all three parameters (street, zip, unit) carry their own descriptions, so the schema does the heavy lifting. The description only gestures at 'street address' generically and adds no format or validation detail beyond what the schema already provides; 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+resource (check fiber availability at a street address) and adds domain context that disambiguates the business relationship (Fast Fibre is the local service, Brightspeed owns the network). An agent immediately knows what the tool answers and can distinguish it from request_callback, which this tool feeds into.

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?

Usage context is implied rather than stated: the description notes whether a call can be requested, which hints at the handoff to request_callback, and 'Free, no sign-up' lowers the barrier to calling it. However it never explicitly says when to use this versus request_callback or states any exclusion, so the agent must infer the routing.

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 a non-readonly, idempotent, open-world action, and the description adds substantial context beyond them: the mandatory consent gate, that a specialist calls the same day, that nothing is ordered until the person confirms on that call, and that the result message (including any confirm link) must be relayed back.

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?

Purpose and the core constraint are front-loaded and every sentence carries operational weight (consent, next step, result relay). However, the consent sentence largely restates the user_confirmed schema text verbatim, adding some redundancy and length.

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 no output schema, the description still covers prerequisites, consent, what happens next, and how to handle the result, which is thorough. Its one gap is that it never ties into the check_fiber_availability sibling or states whether availability should be verified before requesting a callback.

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; the description still adds meaning by constraining name and phone ('as they gave it', 'never guess it') and by explaining that user_confirmed may only be true after the person requested the call and agreed to the quoted consent text.

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 opening sentence states a specific verb and resource: asking Fast Fibre to call a person about fiber internet at their address. It is clearly distinct from check_fiber_availability in practice, but the description never names that sibling, so an agent must infer the relationship between the two tools.

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 explicit when-to-use and when-not-to-use conditions: only when the person asked for the call, with their own name and mobile number, never guessing them. It also dictates the exact consent step and the required user_confirmed flag before calling.

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