Skip to main content
Glama

Datasource Dependencies

datasource_dependencies
Read-only

Inspect calculated-field dependency graphs, reverse edges, and cycles in a datasource before changing formulas; optionally test expression overrides to detect proposed cycles.

Instructions

Inspect datasource formula field graph, reverse edges and one cycle if found.

Validates each calculated field sequentially; cost grows with formula count. Requires matching draft/published. Validation failures produce partial output, never proof of no dependencies. Does not cover report consumers or parameters and does not authorize field deletion. No source/report mutation. Optional overrides replace expressions in the inspected graph only, using fully qualified field_id (t0.calc_*). Detects proposed cycles, but expression types are validated against the CURRENT source, not propagated future types.

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": {
      "datasource_id": "<datasource_id>"
    },
    "name": "datasource_dependencies"
  }
}

Input Schema

NameRequiredDescriptionDefault
overridesNo
report_idNo
datasource_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.5

TDQS

A4.3/5.0
Behavior5/5

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

With only readOnlyHint available, the description carries the behavioral burden and does so richly: sequential validation with cost growing per formula, partial output on validation failure that is 'never proof of no dependencies,' one-cycle-only detection, and types validated against the CURRENT source rather than propagated future types. These are exactly the caveats an agent needs to avoid over-trusting a clean result, and 'No source/report mutation' is consistent with readOnlyHint=true.

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 first sentence front-loads the purpose and outputs before the caveats, and nearly every clause adds distinct information. It is dense and somewhat long, with mild redundancy between 'No source/report mutation' and 'does not authorize field deletion,' which the readOnlyHint already partly covers.

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?

Given an output schema exists, the description need not explain return values, yet it still characterizes them (reverse edges, single cycle) and covers cost, failure semantics, and scope exclusions. The only meaningful omission is the unspecified report_id parameter, which leaves one input unexplained for an otherwise well-covered tool.

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 0% across three parameters, so the description must compensate. It does well for overrides, explaining they replace expressions in the inspected graph only and must use fully qualified field_id (t0.calc_*), but the report_id parameter is never mentioned and datasource_id is only implicit, leaving a real gap.

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 opens with a specific verb and resource: 'Inspect datasource formula field graph,' and names exactly what is returned — reverse edges and one cycle if found. That distinguishes it cleanly from the sibling calculated-field mutation tools (create/edit/delete), which do not inspect graphs.

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?

It carves out scope explicitly: no report consumers, no parameters, no field deletion authorization, and no source/report mutation, which steers an agent away from misuse. It also states the draft/published matching prerequisite. It stops short of naming an alternative tool for deletion or consumer analysis, so it is clear context without explicit routing.

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

Deploy Server

Other Tools