Skip to main content
Glama

Monitoring alerts

monitoring_alerts
Read-only

What is firing or pending now in a project's monitoring (get_monitoring): each alert's name, state, severity, labels (host, instance…), summary and since when, firing first — the Prometheus data source's alerting rules and Grafana's own, as Grafana lists them. Where the rule list is not open to the token, the ALERTS series say what fires, without summaries. For the people who work in the project and the company; at most 60 reads of a project's monitoring an hour, agents and people together. A refusal has a 'state': not_connected (with the 'url' of the screen that connects one), off, refused, sealed, unreachable, busy, too_big, missing, no_access, not_found, bad_request.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project": "<project>"
    },
    "name": "monitoring_alerts"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectYesProject key, e.g. 'PM'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior4/5

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

Goes well beyond the annotations: a concrete rate limit (at most 60 reads of a project's monitoring per hour, shared between agents and people), a documented degraded mode where unreadable rule lists fall back to the ALERTS series without summaries, and an enumerated set of refusal states including not_connected carrying a connecting 'url'. The only shortfall is that ordering/edge behavior beyond 'firing first' and empty results is unstated.

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

Conciseness4/5

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

Front-loaded with the answer an agent needs (what is firing now, in what order, with what fields) and no padding sentences. The phrasing is telegraphic and comma-spliced, which costs some readability but every clause carries information.

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 no output schema, the description supplies the return shape itself (per-alert fields plus sort order), the failure surface (named refusal states and the not_connected url), and the throughput ceiling. An agent can call this correctly and interpret both success and refusal without further sources.

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

Parameters3/5

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

Only one parameter, 'project', fully documented in the schema at 100% coverage, so the schema carries the semantics. The description adds only that it is 'a project's monitoring' and illustrates nothing about key format beyond what the schema already gives.

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

Purpose4/5

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

States a specific resource and scope: current firing or pending alerts in one project's monitoring, with the fields returned (name, state, severity, labels, summary, since). It also names the data sources covered (Prometheus rules plus Grafana's own). Slightly murky because it cites 'get_monitoring' in parentheses, which reads like an implementation note rather than a differentiation from the sibling of that name.

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

Usage Guidelines3/5

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

'What is firing or pending now' implies a current-state-only use, distinguishing it implicitly from historical querying via monitoring_query, but the alternative is never named. The audience line ('for the people who work in the project and the company') and the hourly read budget give operating context rather than when-to-use vs when-not.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources