Skip to main content
Glama

Monitoring hosts

monitoring_hosts
Read-only

The ready-made question: availability and load of a project's servers over the last day or week, from its monitoring (get_monitoring) — per host its availability (% of scrapes answered), load per core, CPU busy %, memory used %, root disk used % (average, worst and now) and the processes the kernel killed for memory. Answers the PromQL it ran ('queries') and 'source': the Grafana, the data source, when it was asked and the period counted. Ask this before writing PromQL of your own. 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_hosts"
  }
}

Input Schema

NameRequiredDescriptionDefault
periodNo'day' (default) or 'week'.
projectYesProject key, e.g. 'PM'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description adds real value beyond that: a concrete rate limit (60 reads/hour shared by agents and people) and a full enumeration of refusal states (not_connected with a 'url', off, refused, sealed, unreachable, busy, too_big, missing, no_access, not_found, bad_request), which tells the agent how to interpret failures. Return fields are also disclosed, though no output schema exists to compare against.

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-loads the core question and the returned metrics before the guidance and error enumeration, so an agent can act on the first clause. It is dense and the long trailing list of refusal states plus quoted field names ('queries', 'source') adds bulk, but each element carries usable information.

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

Completeness4/5

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

With no output schema, the description takes on the burden of describing returns and does so field by field, and it explains error handling and rate limits. It is close to complete for a two-parameter read tool, with only minor gaps such as pagination or result-size limits beyond the 'too_big' state.

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?

Schema description coverage is 100% and both parameters are documented in the schema itself, including the 'day'/'week' values for period. The description only restates the time window ('last day or week'), adding no new semantics such as timezone or boundary behavior, so the baseline 3 applies.

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?

Names a specific resource and scope ('availability and load of a project's servers over the last day or week') and enumerates exactly what each host row contains (availability %, load per core, CPU busy, memory, root disk, OOM kills). It also distinguishes itself from the sibling that runs arbitrary queries by saying 'Ask this before writing PromQL of your own.'

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?

Explicitly states the preferred ordering versus writing your own PromQL, and names the audience ('people who work in the project and the company') plus the 60-reads-per-hour cap that constrains repeated calls. No explicit when-not-use case versus get_monitoring itself, which keeps it 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.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources