Skip to main content
Glama
Arkanji

iWork Studio MCP Server

by Arkanji
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Numbers: recalculate

numbers_recalculate
Destructive

Recompute every formula in a Numbers file after edits made without the app, so results reflect current values. Run only when the file reports formulas_need_recalc.

Instructions

Make Numbers recompute every formula from the current values. Numbers keeps showing a formula's old result after edits made without it (numbers_edit_cell, numbers_insert…), so run this after those when the file has formulas — their result says so (formulas_need_recalc). Formulas and inputs are verified unchanged. Needs macOS + Numbers, file closed. dry_run=true previews the change on a copy without touching the file. Use only after a no-app edit returned formulas_need_recalc, so totals are current. Not needed after numbers_set_formula, which recalculates itself.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesPath to the .numbers file (absolute, or starting with ~).
dry_runNotrue = make the change on a throwaway copy, run every check, and return what would change; the file itself is not touched. Use it before broad or risky edits and show the user.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv2.4.1
    • addedInput schema / properties / dry_run / description
      Added value: +"true = make the change on a throwaway copy, run every check, and return what would change; the file itself is not touched. Use it before broad or risky edits and show the user."
    • addedInput schema / properties / path / description
      Added value: +"Path to the .numbers file (absolute, or starting with ~)."
  2. First observedv2.4.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only flag it as non-read-only and destructive; the description adds that outputs are verified unchanged, that it requires macOS + Numbers with the file closed, and that dry_run operates on a throwaway copy. That is meaningful context beyond the annotation block.

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 core action and tightly packed with prerequisite and routing information, though the parenthetical sibling list and the dry_run sentence add length that slightly dilutes the opening.

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 an output schema present, return values need not be explained. The description nonetheless covers the trigger signal, the platform/file-state prerequisites, and the dry-run escape hatch, leaving nothing an agent needs missing.

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 100% and the schema already documents both path and dry_run, including the throwaway-copy behavior. The description largely restates dry_run's contract rather than adding syntax, defaults, or edge cases the schema lacks, so baseline 3 applies.

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 action and resource: recompute every formula in a Numbers file from current values. It immediately distinguishes itself from write-oriented siblings by naming numbers_edit_cell and numbers_insert as the operations that leave stale results behind.

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?

Explicit trigger condition (run only after a no-app edit returned formulas_need_recalc), an explicit exclusion (not needed after numbers_set_formula, which recalculates itself), and a preview path via dry_run. An agent can decide whether to call this without guessing.

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