Is GitHub, npm, Cloudflare or your AI provider down right now? 20 status pages, one call.
Scored across 3 tools
Each tool has a clearly distinct purpose: listing supported services, checking one named service, and checking all services at once. Even though check_all_services and check_service_status both check status, the all-vs-one distinction is obvious and reinforced by the descriptions.
All tool names follow a consistent verb_noun pattern: check_all_services, check_service_status, and list_supported_services. The naming clearly indicates both the action and the target, making the set predictable.
Three tools is a well-scoped set for a simple uptime/status-checking server. Each tool serves a distinct and necessary purpose with no redundancy or bloat.
The tool surface fully covers the domain: discovery of supported services, checking a single service, and checking all services. There are no obvious gaps for the stated purpose, and unsupported arbitrary URLs are explicitly disallowed.
Is anything I depend on broken right now?
Checks every supported provider in parallel and returns a one-sentence summary plus per-service detail. Use this first: it answers the whole question in one call. Optionally narrow with ?services=github,npm. A provider whose status page cannot be read is reported as "unknown", never as healthy.
| Name | Required | Description | Default |
|---|---|---|---|
| services | No | Optional comma-separated slugs to narrow the check, e.g. "github,npm,cloudflare". Omit to check all. |
| Name | Required | Description |
|---|---|---|
| down | No | Slugs with a major or critical incident open. |
| checked | Yes | How many services were checked. |
| summary | Yes | One sentence answering "is anything broken right now", safe to show verbatim. |
| unknown | No | Slugs whose status page could not be read. |
| degraded | No | Slugs with a minor incident open. |
| services | Yes | Full per-service detail. |
| all_operational | Yes | True only when every checked service reports no known problems AND every status page was reachable. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds valuable behavioral detail beyond that: parallel checking, the returned summary-plus-detail shape, optional narrowing, and especially the guarantee that unreadable providers are reported as 'unknown' rather than healthy.
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 compact and front-loaded with purpose. Every sentence earns its place: the problem framing, the parallel-check behavior, the 'use first' guidance, the optional parameter, and the important unknown-status semantics.
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 simple tool with one optional parameter and an output schema, the description is complete. It tells the agent what will happen, how to narrow scope, how failures are represented, and how this tool fits into the overall workflow, leaving no important gap.
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 schema already documents the services parameter at 100% coverage. The description adds meaning beyond the schema by giving concrete example slugs ('github,npm'), explaining that omission checks all providers, and tying the parameter to the behavior of narrowing the check.
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: it checks every supported provider in parallel and returns a one-sentence summary plus per-service detail. The opening user-focused question frames the purpose, and the scope is distinct from the sibling check_service_status, which is for a single provider.
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 description gives clear usage context with 'Use this first: it answers the whole question in one call' and explains optional narrowing via the services parameter. It does not explicitly name when to use the sibling check_service_status or list_supported_services instead, so it falls just short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Current incident state for one named service.
Returns the normalised state (operational, degraded, down, unknown), the provider's own description, and a link to the full status page. Use when you already know which provider you care about.
| Name | Required | Description | Default |
|---|---|---|---|
| service | Yes | Slug of the service to check. One of: github, npm, cloudflare, anthropic, openai, vercel, netlify, render, supabase, mongodb, digitalocean, docker, circleci, sentry, datadog, twilio, atlassian, bitbucket, discord, hashicorp. |
| Name | Required | Description |
|---|---|---|
| name | Yes | Human name of the provider. |
| state | Yes | Normalised state. "unknown" means the status page could not be read, NOT that the service is down. |
| cached | No | Whether this answer came from the 45 second cache rather than a fresh fetch. |
| healthy | No | True when operational, false when degraded or down, null when unknown. |
| meaning | Yes | Plain-language reading of the state, safe to show a user verbatim. |
| service | Yes | The slug that was checked. |
| indicator | No | Raw statuspage.io indicator: none, minor, major or critical. |
| reachable | Yes | Whether the status page itself answered. |
| updated_at | No | When the provider last updated the page (ISO 8601). |
| description | No | The provider's own one-line summary, when it publishes one. |
| status_page | No | URL a human can open to read the full incident history. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish the tool is read-only, idempotent, and non-destructive. The description adds useful behavioral context by disclosing what the response contains: normalized state, provider description, and a status page link. This goes beyond the annotations and clarifies the tool's observational nature.
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 two sentences with no filler. The core purpose is front-loaded in the first sentence, and return-value details follow immediately, making it easy to parse and act on.
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 single-parameter read-only tool with a complete input schema, an output schema, and clear annotations, the description covers purpose, usage context, and return format. Nothing essential is missing for an agent to select and invoke 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 description coverage is 100%, with the service parameter fully documented via enum and description. The tool description adds no extra semantic detail about the parameter, so it stays at the baseline of 3.
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 clearly states the tool returns the current incident state for one named service, listing the specific normalized states and complementary details. It differentiates from siblings by emphasizing 'one named service,' which contrasts with check_all_services and list_supported_services.
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 phrase 'Use when you already know which provider you care about' provides a clear usage context and implicitly steers the agent away from list_supported_services or check_all_services. It does not explicitly name alternatives or state when not to use it, so it falls short of a 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Which services can be checked.
Lists every supported slug with its human name and status page URL. The list is fixed; arbitrary URLs are not accepted.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| count | No | |
| services | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context: the list is fixed, arbitrary URLs are not accepted, and the output contains specific fields. This goes beyond the annotations.
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 short sentences, no filler, and the key purpose is front-loaded in the first line. Every sentence adds value: one defines what the tool lists, the other clarifies the fixed nature and rejection of arbitrary URLs.
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 parameterless list endpoint with an output schema and read-only annotations, the description covers what the tool returns, the fixed scope, and a key constraint. Nothing an agent needs to select and call it 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?
The tool has zero parameters, so the baseline is 4. The description correctly indicates that no input is needed and reinforces that only fixed supported slugs are valid, which is relevant for any future parameter expectations.
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 clearly states the tool's function: listing every supported slug with its human name and status page URL. The phrase 'Which services can be checked' immediately frames the resource and scope, and this differs clearly from the sibling checking 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?
The opening question establishes the use case: discovering which services can be checked. It does not explicitly name sibling alternatives, but the contrast with check_all_services and check_service_status is implicit and sufficient for a zero-parameter discovery tool.
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_all_servicescheck_service_statuslist_supported_servicesReal-time status for 75+ AI services (OpenAI, Anthropic, Cursor). No auth, CORS-enabled.
Live status for 172 cloud and SaaS vendors from their official feeds. Is it you, or is it them?
Live status probes plus published uptime and incident history for 280+ APIs and cloud services.
Live status and health checks for AI coding providers: Claude, Cursor, Copilot, Codex and more.
Add one secure layer between your agents and this server.
