Skip to main content
Glama
basis1: Excel engine for AI agents (formulas, recalculation, audit)

basis1: Excel engine for AI agents (formulas, recalculation, audit)

Official

Trace dependencies

trace_dependencies
Read-only

Trace formula references from one cell to the cells it reads or the cells that read it, up to five levels deep, to explain values, locate errors, or see input impact.

Instructions

Follow formula references from one cell in a session, breadth first, up to depth levels (1-5): direction "precedents" walks to the cells it reads, "dependents" to the cells that read it, and "both" (the default) does each. Returns {root, direction, max_depth, levels: [{depth, nodes: [{cell, formula, value, value_type}]}]} for one direction, or precedents and dependents (each a levels list) in place of levels for "both"; ranges are expanded to single cells and each cell is listed once per direction. Use it to explain where a number comes from, find the source of an error, or see what an input affects. For a cell's own formula use get_formula_range; for the whole graph at once use inspect_model with include_edges.

Input Schema

NameRequiredDescriptionDefault
cellYesCell reference, optionally with sheet prefix (e.g. "B4" or "Sheet1!B4")
depthNoHow many levels deep to trace (default 1, max 5)
directionNo"precedents" for the cells this cell reads, "dependents" for the cells that read it, "both" for each (default "both")both
session_idYesSession ID returned by create_session (list_sessions shows the open ones)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.3.2
    • changedInput schema / properties / direction / description
      Previous value: -"Which direction to trace (default \"both\")"New value: +"\"precedents\" for the cells this cell reads, \"dependents\" for the cells that read it, \"both\" for each (default \"both\")"
    • changedInput schema / properties / session_id / description
      Previous value: -"Session ID"New value: +"Session ID returned by create_session (list_sessions shows the open ones)"
  2. First observedv0.3.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description stays consistent while adding real depth: the exact return shape, range expansion to single cells, and one-listing-per-direction dedup, which the agent cannot infer from any structured field. It stops short of stating what happens for a cell with no formula or an invalid cell reference, leaving a small behavioral gap.

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-loaded with the action and direction modes, and no sentence is filler — the return-shape sentence is justified because no output schema exists. It is a dense wall of text, though; the direction and return-format material would read better as short separated clauses.

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 carries the burden of explaining the response, and it does so thoroughly, including the divergent shape for direction="both". What is missing is minor edge behavior (leaf cells with no formula, invalid cell handling, session expiry), not core calling information.

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%, so cell, depth, direction, and session_id are all already documented, including the enum meanings and the 1-5 bound. The description restates the direction semantics and depth range rather than adding new meaning such as behavior at the depth boundary. Baseline 3 is appropriate when the schema does the work.

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?

States a specific verb and resource — 'Follow formula references from one cell in a session, breadth first' — and immediately disambiguates the three traversal modes (precedents, dependents, both). An agent can tell this apart from get_formula_range and inspect_model from the description alone.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete use cases ('explain where a number comes from, find the source of an error, or see what an input affects') and explicitly routes to alternatives: get_formula_range for a cell's own formula, inspect_model with include_edges for the whole graph. When-to-use and when-not-to-use are both present.

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