Check if fiber internet reaches a home in Hinesville & Midway, GA, and request a specialist's call.
Scored across 2 tools
The two tools have clearly distinct purposes: one checks availability, the other requests a callback. There is no overlap in their actions or outcomes, so an agent can easily select the right tool.
Both tool names use a consistent verb_noun snake_case pattern: check_fiber_availability and request_callback. This predictable naming makes the set easy to parse and remember.
Two tools cover the server's narrow purpose (check availability and request a callback), but the count is slightly under the typical 3–15 range. For this specific domain, however, the minimal set is reasonable and each tool earns its place.
The full workflow for this domain is covered: check availability at an address and, if desired, request a callback. There are no obvious missing operations such as update or delete because the service does not involve persistent user-managed records.
Check whether fiber internet is available at a street address. Fast Fibre is an independent local service in Hinesville & Midway, GA; the fiber network is Brightspeed's. Free, no sign-up. Returns the status, a summary to tell the person, the speeds the block can get and whether a call can be requested. Prices are never quoted online: a specialist tells them on the call.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | Yes | 5-digit ZIP code | |
| unit | No | Apartment or unit, if any | |
| street | Yes | House number and street, e.g. "511 Azalea St" |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark it read-only and non-open-world, but the description adds real behavioral context: no pricing is quoted online, a specialist quotes on the call, and the response includes status, a talk-track summary, speeds, and call-request eligibility. Geographic limitation to Hinesville & Midway is useful and consistent with openWorldHint=false.
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-loads the core action, then layers scope, cost, and return contents in short sentences. Mostly earns its space, though the pricing/specialist sentence is slightly tangential to the check operation itself.
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 compensates by enumerating what comes back (status, summary, speeds, call eligibility) and explains the no-online-pricing policy. 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%, so street, zip, and unit are already documented with formats and examples. The description adds nothing about parameter syntax or constraints, 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 (check) and resource (fiber internet availability) plus the required input (street address). The added business context (Fast Fibre / Brightspeed network, Hinesville & Midway GA) makes the scope unambiguous and distinguishes it from the request_callback sibling.
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?
Conveys when this tool applies (free, no sign-up, checking a specific address) and implies the follow-up path via 'whether a call can be requested.' It stops short of explicitly naming request_callback as the alternative for booking a call, so it's clear context without full routing guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Ask Fast Fibre to call the person about fiber internet at their address. Only when the person asked you to, with their own name and mobile number — never guess them. Before calling this tool, tell the person and get their yes to: "The person asked their AI assistant to request a call from Fast Fibre about fiber internet at this address, and agreed that Fast Fibre may call them at this number to confirm the request." Then set user_confirmed to true. A specialist calls usually the same day to confirm the request; nothing is ordered until the person confirms on that call. Relay the message in the result to the person, with the confirm link if there is one.
| Name | Required | Description | Default |
|---|---|---|---|
| zip | Yes | 5-digit ZIP code | |
| name | Yes | The person's name, as they gave it | |
| plan | No | "500" = 500 Mbps, "1g" = 1 Gig, "2g" = 2 Gig, "help" = not sure yet (default) | |
| unit | No | Apartment or unit, if any | |
| agent | No | Your name as an assistant, e.g. "ChatGPT" or "Claude" | |
| phone | Yes | The person's 10-digit US mobile number, as they gave it. Never guess it. | |
| extras | No | "wifi" = whole-home Wi-Fi, "phone" = home phone | |
| street | Yes | House number and street, e.g. "511 Azalea St" | |
| best_time | No | When the person prefers a call | |
| situation | No | "xfinity" = switching from Xfinity, "other" = from another provider, "moving" = moving in / no internet | |
| user_confirmed | Yes | true only after the person asked you to request the call and agreed to this: The person asked their AI assistant to request a call from Fast Fibre about fiber internet at this address, and agreed that Fast Fibre may call them at this number to confirm the request. |
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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_fiber_availabilityrequest_callbackCheck internet providers, plans, speeds, and known pricing at a specific U.S. street address.
US telecom availability and intelligence by address, with FCC provenance. Fiber-first.
Book a call with 904 Digital Media (Jacksonville, FL): services, open times, requests.
Broadband availability, providers, speeds, and BEAD classification from the FCC
Add one secure layer between your agents and this server.
