Is my broadband down? Live UK provider status and the last 30 days of outages
Scored across 3 tools
The three tools split cleanly along history vs. current status, and all-providers vs. single-provider. The only mild overlap is between get_outage_overview and get_provider_outage_status, but the descriptions explicitly steer one to the other ('for one provider in detail use get_provider_outage_status').
All three names follow a consistent get_outage_* / get_provider_outage_* snake_case verb_noun pattern with the same get_ prefix. The longer name still reads predictably within the same convention.
Three tools is a tight, well-scoped set for a narrow read-only outage lookup domain and avoids redundancy. It is on the lean side, but each tool earns its place rather than feeling padded or thin for the stated purpose.
The surface covers the core lifecycle of outage queries: current status for all providers, current detail for one provider, and 30-day history. Minor gaps exist (no location-based search, no provider directory listing apart from the overview), but agents can work around these.
Use when the user asks about past broadband outages: how often a provider went down recently, what happened on a given day or which providers had problems lately. Returns the incidents each provider's FindBroadband page lists, current first then newest first, with when they started and were resolved, where and the provider's own words, plus a count per provider when no provider is given. For providers whose status page we can't read, days with only public reports appear as public_reports entries. Covers the last 30 days only; say so if asked about anything older. Public reports are unconfirmed.
| Name | Required | Description | Default |
|---|---|---|---|
| date | No | Only incidents that touched this UK calendar day, as YYYY-MM-DD. Must be within the last 30 days. Overrides days. | |
| days | No | How many days to look back, counting today, up to 30. Leave it out for everything we hold (the last 30 days). | |
| provider | No | Only incidents for this provider. Leave it out to search every provider we track. |
| Name | Required | Description |
|---|---|---|
| to | No | |
| days | No | |
| from | No | |
| note | Yes | |
| entries | Yes | |
| page_url | Yes | |
| provider | No | |
| truncated | Yes | |
| checked_at | Yes | |
| to_date_uk | No | |
| by_provider | No | |
| entry_count | Yes | |
| from_date_uk | No | |
| provider_name | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover safety (readOnly, idempotent, non-destructive), but the description adds rich behavioral context: the ordering of results (current first then newest first), the structure of returned data (start/resolution times, location, provider's own words), the count-per-provider behavior when no provider is specified, how unreadable status pages are handled (public_reports entries), and that public reports are unconfirmed. This goes well beyond what annotations provide.
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 description is a single dense paragraph, front-loaded with the primary use case and scope. Every sentence adds useful information about return structure or constraints. It could be split for readability, but there is no wasted text.
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 a tool with 3 optional parameters, full schema coverage, an output schema, and annotations covering safety, the description completes the picture by explaining result ordering, data provenance, edge cases (unreadable status pages), and temporal limits. Nothing needed to invoke correctly 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 schema documents all three parameters. The description adds semantic context about how results behave when provider is omitted (count per provider) and reinforces the 30-day constraint that applies to date and days. It doesn't add format details beyond the schema, but the behavioral context for parameter interactions is valuable.
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 (retrieve past broadband outages) with a precise scope (last 30 days) and explicitly frames the user questions it answers. It distinguishes itself from siblings like get_outage_overview and get_provider_outage_status by focusing on historical incidents rather than current status.
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?
The opening sentence gives clear context for when to use this tool: user asks about past outages, frequency, or which providers had problems recently. It does not explicitly name the sibling tools as alternatives or state when not to use this, but the temporal scoping ('past', 'last 30 days') implicitly differentiates it from current-status siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use when the user asks if there is a broadband outage right now without naming a provider, or wants the current status of UK broadband providers. Returns the FindBroadband hub's own board: every provider we track with its status (Down, Issues earlier or Working fine), where the problem is when the provider named a place, the hub's headline and a link to each provider's page. Down includes incidents limited to the places named, so always say where. For one provider in detail use get_provider_outage_status.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| note | Yes | |
| as_of | Yes | |
| stale | Yes | |
| hub_url | Yes | |
| as_of_uk | Yes | |
| headline | Yes | |
| providers | Yes | |
| checked_at | Yes | |
| down_count | Yes | |
| issues_earlier_count | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the burden is lower. The description adds genuinely useful interpretation semantics — that 'Down' may include incidents limited to named places and that the agent should always state where — which is not derivable from annotations or schema.
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 when-to-use trigger, then the return content, then the sibling routing. Efficient overall, though the third sentence is dense and lists several return fields in one breath rather than cleanly separating them.
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 not be explained, yet the description still supplies the interpretation rule for the status values and the routing to the sibling. For a no-parameter, read-only tool this is complete.
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?
The tool takes zero parameters, so there is nothing for the description to disambiguate. Baseline 4 applies; the description neither omits nor misstates any parameter meaning.
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 concrete verb+resource ('current status of UK broadband providers') and scopes it precisely to an unnamed-provider, all-providers view. It explicitly distinguishes itself from get_provider_outage_status, so an agent can pick correctly without opening either 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?
Gives an explicit trigger ('when the user asks if there is a broadband outage right now without naming a provider') and names the alternative plus its selecting condition ('For one provider in detail use get_provider_outage_status'). No inference required.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use when the user asks whether a specific broadband provider is down, having problems or has an outage, e.g. 'is BT down?' or 'Virgin Media not working'. Returns what that provider's FindBroadband page shows: the status and its headline, the current incidents and the most recent past ones in the provider's own words with the places they named, a day by day picture of the last 30 days and links. Quote the headline and the provider's words as given rather than rewording them. When status_based_on is public_reports we can't read the provider's own status page: Down means people are reporting problems, which the provider hasn't confirmed, and Working fine means nobody is reporting problems, not that the provider has said all is well. Never tell the user their own line is or isn't affected: say what has been reported and where, and point them to the provider's status page or the provider if they are still offline.
| Name | Required | Description | Default |
|---|---|---|---|
| provider | Yes | The broadband provider the user means, as they said it (e.g. 'BT', 'Virgin Media', 'zen'). Free text is fine. |
| Name | Required | Description |
|---|---|---|
| as_of | Yes | |
| place | No | |
| detail | Yes | |
| status | Yes | |
| as_of_uk | Yes | |
| headline | Yes | |
| page_url | Yes | |
| provider | Yes | |
| checked_at | Yes | |
| down_since | No | |
| last_30_days | Yes | |
| down_since_uk | No | |
| provider_name | Yes | |
| past_incidents | Yes | |
| status_based_on | Yes | |
| current_incidents | Yes | |
| past_incident_count | Yes | |
| provider_status_page | No | |
| current_incident_count | Yes | |
| shares_status_page_with | No | |
| provider_status_page_needs | No | |
| current_incidents_truncated | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description layers on substantive behavior beyond that: the status_based_on=public_reports caveat that 'Down' means unconfirmed user reports rather than provider confirmation, the instruction to quote the headline verbatim, and the explicit prohibition on telling a user their own line is affected. These are non-obvious semantic constraints an agent could easily get wrong.
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 and examples before moving to return shape and then the important caveats, so a skimming agent gets what it needs first. It is longish (~150 words), but each sentence carries distinct operational value (quoting rule, public_reports semantics, line-level disclaimer) rather than padding.
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-value documentation is optional, yet the description still orients the agent on what comes back (status, headline, incidents, 30-day picture, links). Combined with the interpretation caveats, nothing needed to call and correctly use this tool 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% and the 'provider' parameter is already well documented in the schema ('as they said it... free text is fine'), so the schema carries the load. The description adds no syntax, format or resolution guidance beyond what the schema states, so the baseline of 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 ('is a broadband provider down / having problems') and anchors it with concrete example queries ('is BT down?', 'Virgin Media not working'). An agent can immediately tell this is a per-provider status lookup rather than a general outage feed.
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?
Explicitly names the trigger condition ('Use when the user asks whether a specific broadband provider is down, having problems or has an outage') with example phrasings, which is strong. However it never references the sibling tools get_outage_history or get_outage_overview, so the agent gets no guidance on when to prefer this provider-scoped tool over those aggregate/history tools.
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.
get_outage_historyget_outage_overviewget_provider_outage_statusLive service status, active incidents, search, and outage history from Downtester.
Live status for 172 cloud and SaaS vendors from their official feeds. Is it you, or is it them?
Live cloud/SaaS outages, provider reliability and exploited CVEs from official status pages and CISA
Website uptime monitoring: live status, uptime reports, incidents, response times, failed checks
Add one secure layer between your agents and this server.
