Skip to main content
Glama
Grist MCP Server
by nic01asFr

Validate Schema

validate_schema

Validates a Grist schema without creating it, checking syntax, target tables, visible and reverse column conflicts, and empty choice columns.

Instructions

Valide un schéma sans le créer.

Vérifie:

  • Syntaxe du schéma

  • Existence des tables cibles pour les références

  • Existence des colonnes visibles ('visible') dans les tables cibles

  • Absence de conflit pour les colonnes inverses ('reverse')

  • Colonnes Choice/ChoiceList sans choix (avertissement)

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>",
      "schema": "<schema>"
    },
    "name": "validate_schema"
  }
}

Input Schema

NameRequiredDescriptionDefault
doc_idYesL'ID du document (pour vérifier les tables existantes)
schemaYesSchéma à valider (format dict)

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.2.2
    • addedInput schema / properties / doc_id / description
      Added value: +"L'ID du document (pour vérifier les tables existantes)"
    • addedInput schema / properties / schema / description
      Added value: +"Schéma à valider (format dict)"
  2. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does a solid job: it explicitly says the schema is NOT created, so the agent knows this is non-mutating, and it itemizes what is verified, including that empty Choice/ChoiceList columns only produce a warning rather than an error. It does not mention permissions or how failures are surfaced, but the output schema covers return values.

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 key distinction (validates without creating) is front-loaded in the first line, followed by a tight bulleted list of checks with no filler. Only minor gain possible from trimming the mixed-language framing.

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?

Both parameters are described, an output schema exists so return values need no narrative, and the check list gives the agent sufficient expectation of outcomes. A note on error behavior or a pointer to create_schema would make it complete.

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 doc_id and schema are already documented in the input schema, and the description adds no format or syntax guidance for the schema object beyond the enumeration of checks. Baseline 3 is appropriate since the structured 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 ('Valide un schéma') and immediately distinguishes itself from schema creation with 'sans le créer'. The five enumerated checks make the tool's scope concrete and distinguishable from siblings like create_schema.

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

Usage Guidelines3/5

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

'Sans le créer' implies the tool is a pre-flight check to be run instead of create_schema, but the description never names create_schema or states when validation is required versus optional. Usage is inferable rather than explicit.

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