Skip to main content
Glama

discover_source

Introspect an upstream connector to preview its proposed source configuration before creating anything, then pass the result directly to source creation. Supports connectors like Prometheus and GitHub.

Instructions

Introspect an upstream and get a proposed source config — no commitment. Works for connectors that can introspect: e.g. prometheus given {"url": "http://..."}, or github given {"repo": "owner/name"}. The returned proposed_config can be passed straight to create_source. (Use list_connectors to see which connectors support discovery.)

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": {
      "connector": "<connector>",
      "config": "<config>"
    },
    "name": "discover_source"
  }
}

Input Schema

NameRequiredDescriptionDefault
configYes
connectorYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.57.0

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose the central behavioral trait — 'no commitment', meaning nothing is persisted — and the create_source handoff, but omits auth requirements, whether the upstream is actually contacted, failure behavior for non-introspectable connectors, and rate limits.

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 action and the 'no commitment' contract, then adds examples and the create_source handoff. Efficient with no filler; the trailing parenthetical about list_connectors is slightly tacked-on but still useful.

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?

An output schema exists, so return-field detail is unnecessary, yet the description still names proposed_config and its destination. Given a free-form nested config object and no annotations, the missing connector identifier format and per-connector config shapes are the main gap.

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 coverage is 0% with both parameters undocumented, and the description only partially compensates: it gives concrete config shapes for two connectors ({"url": "http://..."}, {"repo": "owner/name"}) and implies connector is a name, but never states the accepted connector identifier format or config shapes for other connectors.

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?

Specific verb + resource: introspect an upstream and produce a proposed source config, explicitly 'no commitment'. It names concrete examples (prometheus with url, github with repo/name) and distinguishes itself from create_source by stating the proposed_config feeds it.

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?

States the precondition (connector must support introspection) and directs the agent to list_connectors to find which connectors qualify. It does not explicitly say when to skip discovery and call create_source directly, which keeps it below 5.

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