Skip to main content
Glama
Sign In

OrgGen AI

by ai.orggen
OverviewDiscussionsAdmin

import_data_model

Destructive

Imports a data model from a universal format and turns it into OrgGen entities. Supported parsers: 'dbml', 'sql-postgres', 'json-schema'. Mode 'replace' (default) replaces all existing ERD entities — suited when the user wants to bootstrap the project from a source file. Mode 'merge' adds to the existing entities without touching the old ones — useful to merge a sub-domain. Blocks of the org-chart kind (groups, subsidiaries) are never touched. Returns warnings for unrecognized types (mapped to 'string' by default) and orphan FKs.

Input Schema

NameRequiredDescriptionDefault
modeNo'replace' (default) replaces all existing ERD entities with the imported model. 'merge' adds to the existing entities while avoiding duplicates by name — relations between new and old entities are kept if the names match.
formatYesFormat of the input payload. Supported parsers: 'dbml', 'sql-postgres', 'json-schema'.
originNoTop-left corner of the grid layout (default x=200, y=200).
payloadYesText content of the model to import (the complete source file).
expectedProjectIdNoUUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / expectedProjectId / description
      Previous value: -"UUID du projet visé par CET appel. Cible RÉELLEMENT ce projet au lieu du projet de session. Refusé sans rien modifier si l'accès n'est pas accordé."New value: +"UUID of the project targeted by THIS call. ACTUALLY targets this project instead of the session project. Refused without changing anything if access is not granted."
    • changedInput schema / properties / format / description
      Previous value: -"Format du payload d'entrée. Parsers supportés : 'dbml', 'sql-postgres', 'json-schema'."New value: +"Format of the input payload. Supported parsers: 'dbml', 'sql-postgres', 'json-schema'."
    • changedInput schema / properties / mode / description
      Previous value: -"'replace' (défaut) remplace toutes les entités MCD existantes par le modèle importé. 'merge' ajoute aux entités existantes en évitant les doublons par nom — les relations entre nouvelles et anciennes entités sont conservées si les noms correspondent."New value: +"'replace' (default) replaces all existing ERD entities with the imported model. 'merge' adds to the existing entities while avoiding duplicates by name — relations between new and old entities are kept if the names match."
    • changedInput schema / properties / origin / description
      Previous value: -"Coin haut-gauche du layout grille (par défaut x=200, y=200)."New value: +"Top-left corner of the grid layout (default x=200, y=200)."
    • changedInput schema / properties / payload / description
      Previous value: -"Contenu textuel du modèle à importer (le fichier source au complet)."New value: +"Text content of the model to import (the complete source file)."
  2. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations declare destructiveHint=true, and the description goes well beyond that by specifying exactly what is at risk (all existing ERD entities in 'replace' mode) and what is protected ('org-chart kind blocks are never touched'). It also discloses post-execution behavior (warnings for unrecognized types defaulting to 'string', orphan FKs), which is real behavioral context.

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 purpose, then systematically covers formats, modes, and preservation/warning behavior. Dense but each sentence carries distinct information; only mild redundancy with the schema's own mode/format text.

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?

For a destructive, multi-parameter import tool with no output schema, the description supplies the critical context: input formats, mode semantics, what is preserved, and what warnings are returned. It omits any note on permissions or on how to undo an import (though rollback_import exists as a sibling), leaving a small gap.

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 the schema already documents mode, format, payload, origin, and expectedProjectId. The description restates the parser list and the replace/merge intent but adds little syntax or format detail beyond the schema, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb+resource ('Imports a data model') and specifies the conversion target ('into OrgGen entities') plus the supported input formats. It clearly separates this from generic imports by naming the exact parsers, but it never names its closest siblings (import_arch_diagram, import_org, import_tasks), so the agent must 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 Guidelines4/5

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

Gives explicit when-to-use guidance for the key decision: 'replace' is for bootstrapping a project from a source file, 'merge' is for merging a sub-domain without touching existing entities. It does not cover prerequisites/authorization or point to alternative import tools, but the mode-selection guidance is concrete.

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

All OrgGen AI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources