Skip to main content
Glama

Uptimepage

by dev.uptimepage

Monitor history

get_monitor_history
Read-only

One monitor's history over a window (1h/24h/7d/30d): uptime, latency series, a per-region split of the same window, failures with error text, and incident windows. Pass region to narrow it to one probe region and tell a partial outage from a total one. Read-only.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesThe monitor id (from `list_monitors`).
regionNoNarrow uptime, the latency series, and the region breakdown to one probe region (an id the monitor is assigned to, from `get_monitor.regions`). Omit for every region together.
windowYesTime window: `1h`, `24h`, `7d`, or `30d`.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
regionNoThe region this answer was narrowed to, or `null` for all of them.
uptimeNoUptime percentage over the window. `null` when the window holds no checks — that is unknown, not zero. Unfiltered it counts confirmed incidents; under a `region` filter it is that region's raw check rate, so the two are not comparable.
regionsYesPer-region split of the same window, so a partial outage is visible. Always every region the monitor runs in, including under a `region` filter, and empty when it runs in only one. Regions that ran no checks in the window are omitted; this reads per-minute data, which is kept for 30 days, so at the far edge of a `30d` window a region can be short of samples or absent while the headline numbers still cover it.
failuresYesConfirmed failures on the monitor as a whole. A `region` filter does not narrow these: an incident is raised for the monitor, not per region.
incidentsYesIncident windows on the monitor as a whole, unnarrowed by `region` for the same reason as `failures`.
latency_seriesYes

TDQS

A4.5/5.0
Behavior4/5

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

The readOnlyHint annotation is reinforced by the description's 'Read-only' statement. The description adds valuable behavioral context beyond the annotation by enumerating exactly what data is returned (uptime, latency, region split, failures, incident windows), which helps the agent set expectations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the core purpose and data list, followed by a targeted usage tip for `region`. Every word contributes, with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present and a read-only annotation, the description sufficiently covers the tool's behavior and usage for a straightforward 3-parameter history fetch. It lists return components and parameter rationale, leaving no significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, but description adds semantic value beyond the schema: it reiterates window enum values and explains the diagnostic purpose of `region` (telling partial from total outage), which enriches the parameter's meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: retrieving one monitor's history over a specified window, listing specific data types (uptime, latency series, per-region split, failures, incident windows). This distinguishes it from sibling tools like get_monitor, which likely provides current status.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use this tool (historical data) and gives explicit guidance on using the `region` parameter to differentiate partial from total outages. It does not explicitly name alternatives or state exclusions, but the context is sufficient.

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

All Uptimepage toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.4/5.0
Disambiguation5/5

Each tool targets a distinct resource and action: flow runs, step trends, incidents, incident metrics, monitors, monitor history, org health, org usage, status pages, notification channels, regions, status pages lists, and tags. The get_ vs list_ distinction is consistent and each pair (e.g., get_monitor vs list_monitors) is clearly separated by depth of detail. No two tools appear to serve the same purpose.

Naming Consistency5/5

All tool names follow the verb_noun pattern with snake_case, using only 'get_' for single-item or aggregate detail and 'list_' for collections. Objects are consistently named (monitor, incident, status_page, org_*). This predictive pattern makes it easy to guess tool behavior from the name.

Tool Count5/5

At 15 tools, this server sits at the upper bound of the well-scoped range, yet every tool fills a clear niche: monitoring details, history, incidents, flow-specific analytics, org-level views, and reference data (regions, tags, channels). No tool feels redundant, and the count is appropriate for a read-only monitoring API.

Completeness4/5

The read-only surface is remarkably comprehensive, covering monitors, incidents, flow runs, step trends, status pages, notification channels, regions, tags, and org health/usage. The only notable gap is the lack of any mutation tools (e.g., update_monitor, acknowledge_incident) which the descriptions hint at but do not expose, so agents cannot act on the information—only observe.

Resources