Табуля

files_dependencies

Read-onlyIdempotent

Traces the dependency graph around a cell. 'forward' returns what the code cell at the given cell READS (its input ranges, as 'reads'); 'reverse' returns the code cells that DEPEND ON the given cell (as 'read_by'); 'both' (default) returns both. Use to understand impact before editing a cell or to find a code cell's inputs. Read-only. Signature: files_dependencies(file_uuid, cell, sheet?, direction?).

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": {
      "file_uuid": "<file_uuid>",
      "cell": "<cell>"
    },
    "name": "files_dependencies"
  }
}

Input Schema

Name	Required	Description
`cell`	Yes	Cell in A1 notation, e.g. 'B2'.
`sheet`	No	Sheet name (defaults to the first sheet).
`direction`	No	forward = what the cell reads; reverse = what depends on the cell; both (default).
`file_uuid`	Yes

Output Schema

Name	Required	Description	Default
`file_uuid`	Yes
`dependencies`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 31, 2026

TDQS

A4.1/5.0

Behavior4/5

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

The annotations already declare read-only, idempotent, non-destructive behavior, and the description reinforces 'Read-only.' Beyond that, it explains what each direction mode returns and even names the result keys ('reads', 'read_by'), which is useful behavioral context not carried by annotations. It does not discuss permissions, limits, or edge cases, but the output schema and annotations cover much of that ground.

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 description is front-loaded with purpose, then mode semantics, then use cases. It is compact overall, though the trailing Signature line is somewhat redundant with the input schema and could be trimmed.

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?

For a read-only dependency tracer with an output schema and rich annotations, the description covers what the tool does, how modes differ, and when to use it. It omits error behavior and file_uuid meaning, but those are minor gaps given the structured fields.

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 75%, and the description mostly restates the direction enum semantics that are already documented in the schema. It adds the optional-parameter signature and default behavior, but provides little additional meaning for cell, sheet, or file_uuid beyond what the schema already states.

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 states a specific verb and resource: 'Traces the dependency graph around a cell.' It distinguishes the three direction modes explicitly and differentiates itself from read-oriented siblings by framing use as impact analysis or finding a code cell's inputs.

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 gives clear usage contexts: 'Use to understand impact before editing a cell or to find a code cell's inputs.' This is strong guidance, but it does not name an alternative tool or state when not to use this one.

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

All Табуля tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?