Skip to main content
Glama
RawTree MCP Server

RawTree MCP Server

Official
by rawtreedb

Get Connector Metrics

get-connector-metrics
Read-only

Retrieve stored metric observations for a connector across a configurable recent time window to inspect counters, gauges, and histograms; empty results mean no observations, not zero activity.

Instructions

Purpose: Read stored metric observations for one connector over the last window_seconds (default 300, maximum 3600).

Returns: A raw JSON array from /v1/metrics, filtered by connector ID. Rows retain metric names, timestamps, destination, revision, and collector identities. Metric availability depends on the connector and runtime. An empty array means no observations in this window, not zero activity.

Interpretation: Counters are cumulative; compare observations for the same series and revision, accounting for resets. Histograms and gauges are not counters. No runtime status or synthesized zero values are added.

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": {
      "connectorId": "<connectorId>"
    },
    "name": "get-connector-metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
clusterNoRawTree cluster to use for this operation.
connectorIdYesConnector ID returned by list-connectors or create-connector.
organizationNoRawTree organization containing the target cluster.
window_secondsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.4.9
    • addedInput schema / properties / window_seconds
      Added value: +{
      +  "maximum": 3600,
      +  "minimum": 1,
      +  "type": "integer"
      +}
  2. Addedv0.3.2

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the readOnly/non-destructive annotations, the description discloses the underlying endpoint (/v1/metrics), that output is a raw JSON array, which fields rows retain, that availability varies by connector and runtime, and critically that an empty array means no observations rather than zero activity. The interpretation guidance on cumulative counters, resets, and histograms/gauges is behavioral context an agent cannot get 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.

Conciseness4/5

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

The bolded Purpose/Returns/Interpretation structure is well front-loaded and each section carries distinct information. Minor redundancy exists where the 3600 maximum is restated from the schema, but no sentence is filler and the caveats about empty arrays and counter resets earn their space.

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 carries the burden of explaining returns and does so thoroughly: raw array shape, retained fields, empty-array semantics, and how to read counters versus gauges. For a four-parameter read-only metrics tool, an agent has everything needed to call it and interpret the result.

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 75% and the two identity parameters (connectorId, cluster, organization) are already documented in the schema. The description adds genuine value for the undocumented window_seconds parameter by stating the default (300) and maximum (3600), which the schema's maximum alone does not convey as a default.

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?

The description gives a specific verb and resource ('Read stored metric observations for one connector') plus a bounded scope ('over the last window_seconds'), which is far more precise than the name alone. It implicitly separates itself from a status tool by stating 'No runtime status or synthesized zero values are added', but it never names a sibling such as get-connector, so differentiation requires inference.

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?

Usage context is implied by the purpose and window scoping, and the 'no runtime status' note hints at what this tool is not for. However, there is no explicit when-to-use statement, no named alternative for configuration or status questions, and no prerequisites such as the connector needing to be running or active for metrics to exist.

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