Skip to main content
Glama
Arkanji

iWork Studio MCP Server

by Arkanji
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Numbers: insert

numbers_insert
Destructive

Insert rows or columns into an existing Apple Numbers table at a chosen position, or append them, optionally filled with values; dry_run previews changes.

Instructions

Insert rows or columns (what = rows | columns) before 1-based position at; omit at to append. Optional values: one list per new row (or column). Every existing cell is verified at its new position. In tables with formulas, only appending is allowed (shifting would break references). dry_run=true previews the change on a copy without touching the file. Use to add rows or columns to an existing table (optionally filled). For a separate table use numbers_add_table. In tables with formulas only appending works; do mid-table inserts in Numbers.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
atNo1-based position to insert before; omit to append at the end.
pathYesPath to the .numbers file (absolute, or starting with ~).
whatYesrows | columns.
countNoHow many to insert.
sheetNoSheet name. Omit when the file has one sheet (iwork_read lists sheets and tables).
tableNoTable name on that sheet. Omit when the sheet has one table.
valuesNoOptional contents: one list per new row (or column), e.g. [["Riyadh", 1200]].
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. Changed8 schema fields changedv2.4.1
    • addedInput schema / properties / at / description
      Added value: +"1-based position to insert before; omit to append at the end."
    • addedInput schema / properties / count / description
      Added value: +"How many to insert."
    • 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 ~)."
    • addedInput schema / properties / sheet / description
      Added value: +"Sheet name. Omit when the file has one sheet (iwork_read lists sheets and tables)."
    • addedInput schema / properties / table / description
      Added value: +"Table name on that sheet. Omit when the sheet has one table."
    • addedInput schema / properties / values / description
      Added value: +"Optional contents: one list per new row (or column), e.g. [[\"Riyadh\", 1200]]."
    • addedInput schema / properties / what / description
      Added value: +"rows | columns."
  2. First observedv2.4.0

TDQS

A4.6/5.0
Behavior4/5

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

Adds real behavioral context beyond the annotations: every existing cell is verified at its new position, formula-bearing tables permit only appending, and dry_run previews on a throwaway copy without touching the file. Annotations cover the destructive/non-idempotent profile, and the description does not contradict them; it stops short of stating permission/auth needs or what the returned check report contains.

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 semantics, and most sentences earn their place. However, the formula-table restriction is stated twice ('only appending is allowed' and 'In tables with formulas only appending works'), which is redundant padding in an otherwise tight description.

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?

An output schema exists, so return details need not be described. Combined with the 100%-covered input schema, annotations, and sibling names, the description covers the mutation constraints, the preview mechanism, and the correct alternative tool – nothing an agent needs to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3, but the description still adds value: it glosses `what` (rows | columns), `at` as 1-based with omit-to-append, and gives the nested `values` shape (one list per new row/column, e.g. [["Riyadh", 1200]]). It leaves `count` and the empty-argument cases to the schema.

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 ('Insert rows or columns ... before 1-based position `at`') with clear scope and an explicit routing contrast to numbers_add_table. An agent can distinguish it from siblings like numbers_add_table and numbers_create without opening schemas.

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?

Explicitly names when to use it ('add rows or columns to an existing table, optionally filled') and when not to ('For a separate table use numbers_add_table'), plus the formula-table fallback ('do mid-table inserts in Numbers'). Alternatives and the excluding condition are both stated.

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