Skip to main content
Glama
Grist MCP Server
by nic01asFr

Create Column

create_column

Creates a new column in a Grist table, letting you define its type, label, choices, formula, and display options for structured data.

Instructions

Crée une nouvelle colonne dans une table.

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": {
      "doc_id": "<doc_id>",
      "table_id": "<table_id>",
      "column_id": "<column_id>"
    },
    "name": "create_column"
  }
}

Input Schema

NameRequiredDescriptionDefault
labelNoLibellé d'affichage de la colonne (optionnel)
doc_idYesL'ID du document
choicesNoListe de choix pour Choice/ChoiceList (optionnel)
formulaNoFormule Python pour colonnes calculées (optionnel)
table_idYesL'ID de la table
column_idYesID de la nouvelle colonne (doit être unique dans la table)
column_typeNoType de données. Types supportés: - Text, Numeric, Int, Bool, Date, DateTime - Choice, ChoiceList (avec paramètre choices) - Ref:TableId, RefList:TableId (références) - AttachmentsText
descriptionNoDescription de la colonne (optionnel)
visible_colNocolRef de la colonne à afficher pour les Ref (optionnel)
widget_optionsNoOptions d'affichage comme dict (optionnel)
untie_col_id_from_labelNoDissocier l'ID du label (défaut: True)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changedv0.2.2
    • addedInput schema / properties / choices / description
      Added value: +"Liste de choix pour Choice/ChoiceList (optionnel)"
    • addedInput schema / properties / column_id / description
      Added value: +"ID de la nouvelle colonne (doit être unique dans la table)"
    • addedInput schema / properties / column_type / description
      Added value: +"Type de données. Types supportés:\n- Text, Numeric, Int, Bool, Date, DateTime\n- Choice, ChoiceList (avec paramètre choices)\n- Ref:TableId, RefList:TableId (références)\n- Attachments"
    • addedInput schema / properties / description / description
      Added value: +"Description de la colonne (optionnel)"
    • addedInput schema / properties / doc_id / description
      Added value: +"L'ID du document"
    • addedInput schema / properties / formula / description
      Added value: +"Formule Python pour colonnes calculées (optionnel)"
    • addedInput schema / properties / label / description
      Added value: +"Libellé d'affichage de la colonne (optionnel)"
    • addedInput schema / properties / table_id / description
      Added value: +"L'ID de la table"
    • addedInput schema / properties / untie_col_id_from_label / description
      Added value: +"Dissocier l'ID du label (défaut: True)"
    • addedInput schema / properties / visible_col / description
      Added value: +"colRef de la colonne à afficher pour les Ref (optionnel)"
    • addedInput schema / properties / widget_options / description
      Added value: +"Options d'affichage comme dict (optionnel)"
  2. First observedv0.1.0

TDQS

C2.5/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full behavioral burden, yet it discloses nothing beyond the bare action. It does not state that this is a mutating operation, that column_id must be unique, what happens if it collides, or whether the column can be undone — all of which matter for an 11-parameter write tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The sentence is front-loaded and free of waste, but it is under-specified rather than concise. A single clause for a tool with 11 parameters and a rich type system leaves obvious room for a second clarifying sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 11 parameters, an output schema, and close siblings, this definition is far too thin; the output schema covers only return values. Key confusables — how this differs from create_reference_column, how column_type drives the required choices or formula parameters — go entirely unaddressed.

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 each parameter including column_type's enumerated types, choices, formula, and visible_col is already documented in the schema. The description adds no syntax, defaults, or interaction rules of its own, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ("Crée une nouvelle colonne dans une table"), so the basic action is unambiguous. However, it does nothing to distinguish this tool from the sibling create_reference_column or to indicate what kind of column it creates, leaving an agent to infer the boundary.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no mention of alternatives such as create_reference_column, and no prerequisites (permissions, whether the table must already exist, whether doc_id/table_id must resolve). The lone sentence gives an agent nothing to route on beyond the name.

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