Skip to main content
Glama
Sign In

OrgGen AI

by ai.orggen
OverviewDiscussionsAdmin

move_content_block

Destructive

Moves a content block (contentBlock) from one block to another, KEEPING its id and all its content (no manual retyping needed — that was the blind spot: without this tool, relocating a content block required retyping it by hand in both blocks, an action that has already destroyed a real label in production). sourceCellId===targetCellId is a successful no-op (the content block stays where it is). Exception: if the target block ALREADY carries a content block with that same id (two unrelated content blocks, identical id by coincidence — the content block id is unique per PROJECT, not per block), the moved content block is given a new id so nothing is lost; movedBlockId then reflects the id ACTUALLY persisted, and renamedBlockIds declares it. Any comment thread anchored on this content block (anchor_type='content_block') FOLLOWS the move: its anchor is rewritten to the target block (and to the id actually persisted in case of re-identification), best-effort — a failure on the comments never blocks the move itself.

Input Schema

NameRequiredDescriptionDefault
blockIdYesID of the content block to move (must exist in sourceCellId).
sourceCellIdYesID of the block that currently CARRIES the content block to move.
targetCellIdYesID of the block that must RECEIVE the content block (at the end of its existing contentBlocks).
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. Changed4 schema fields changed
    • changedInput schema / properties / blockId / description
      Previous value: -"ID du bloc de contenu à déplacer (doit exister dans sourceCellId)."New value: +"ID of the content block to move (must exist in sourceCellId)."
    • 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 / sourceCellId / description
      Previous value: -"ID de la cellule qui PORTE actuellement le bloc à déplacer."New value: +"ID of the block that currently CARRIES the content block to move."
    • changedInput schema / properties / targetCellId / description
      Previous value: -"ID de la cellule qui doit RECEVOIR le bloc (à la fin de ses contentBlocks existants)."New value: +"ID of the block that must RECEIVE the content block (at the end of its existing contentBlocks)."
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Goes far beyond the annotations: id preservation, id reassignment on cross-project collision, movedBlockId/renamedBlockIds reporting, comment anchors following best-effort and never blocking the move. The destructiveHint=true annotation aligns with a move that detaches the block from its source.

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, then edge cases in priority order. Dense and largely waste-free, though the parenthetical war story about a destroyed production label is editorial fluff that repeats what the surrounding sentence already says.

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 no output schema, the description supplies the return-field names and their meaning, plus the id-collision branch and the side effect on comment anchors. Nothing material about calling this tool is left undisclosed.

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 the schema already documents all four parameters; the description adds real semantics on top by defining the sourceCellId===targetCellId equality as a successful no-op and clarifying id scope (unique per project, not per block). expectedProjectId is left entirely 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 (moves a contentBlock from source to target block) and immediately differentiates itself from the retyping alternative, i.e. from delete_content_block + add_content_block + update_content_block. An agent can pick it out of a 100+ sibling set without opening the schema.

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?

Clearly frames when to use it ('without this tool, relocating a content block required retyping it by hand') and covers the no-op case (sourceCellId===targetCellId). It does not explicitly name the sibling tools it replaces, so routing is implied rather than stated.

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