Skip to main content
Glama

oto_node_edit

Write a node in the NEW content universe (op=create | update | move | delete). THREE kinds, and only three: page, tableau, ligne (default page). A table row is a node too: create it with kind='ligne', parent_id of its table, and data holding the cell values — data is where user values live, never props, so a column named title cannot overwrite the node's own title. A table's column schema is columns, optional (a free table is a valid table), and re-posting it REPLACES it. Nodes written here are NATIVE: they have no source in the old world, nothing refreshes them, and the old surfaces (oto_doc, oto_project) do not see them — the two universes live side by side during the transition. A page BODY is stored as ordered blocks with STABLE ids, so editing a title never re-identifies the paragraphs and citations survive. scope picks the owner (platform | org | group | user, default user — the node is PERSONAL: no other member sees it, and only an admin of your personal org can view it, read-only and traced: name a scope to make it your org's or your team's) and follows the SAME write ladder as guides; a row has no owner of its own, it takes its table's. move changes parent and rank WITHOUT changing identity — that is what makes children, blocks and inbound references survive. You may only write, move or delete a node you OWN, and only file one under a parent you own: anything else answers the SAME 404 as reading it, unknown and forbidden being indistinguishable. Editing a node that is a COPY of the old world is refused (409): it is edited on its own surface. So is a context layer (a guide, 409), the refusal naming the oto_guide call that writes it. On update, an empty or blank title is refused (400): omit title to keep it. PROVISIONAL surface, like its read side.

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": {
      "op": "<op>"
    },
    "name": "oto_node_edit"
  }
}

Input Schema

NameRequiredDescriptionDefault
opYes
_orgNo
dataNo
kindNo
scopeNo
titleNo
body_mdNo
columnsNo
node_idNo
after_idNo
owner_idNo
parent_idNo
descriptionNo

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4/5.0
Behavior5/5

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

With no annotations, the description carries the full behavioral burden and discloses ownership checks, indistinguishable 404 behavior for unknown/forbidden nodes, default personal scope with admin read-only tracing, column replacement on re-post, stable block IDs, move preserving identity, empty-title rejection, and provisional status. This is unusually rich behavioral context beyond the schema.

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 description front-loads purpose and major modes, and most clauses contain useful information. However, it is a dense single paragraph with nested parentheticals and no clear separation by operation or parameter group, making it harder to scan than necessary.

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

Completeness3/5

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

Given the lack of annotations, output schema, and parameter descriptions, the description does well on behavioral rules and error cases. It still omits the success return shape and node identification details for update/move/delete, and leaves multiple parameters undocumented, so it is adequate but incomplete for a 13-parameter mutation tool.

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

Parameters2/5

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

Schema description coverage is 0% across 13 parameters. The description explains `op`, `kind`, `data`, `columns`, `scope`, `parent_id`, and some title/body semantics, but never explains `node_id` as the target for update/move/delete, `after_id` for rank/position, `owner_id`, `_org`, or `description`; it also refers to `props`, which is not in the schema. These are material gaps for an agent invoking the tool.

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?

The description states a specific verb and resource: 'Write a node in the NEW content universe' and enumerates the four operations create/update/move/delete. It also names the only three kinds and distinguishes these native nodes from the old surfaces `oto_doc` and `oto_project`, so the agent can tell what this tool is for.

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?

It explains the new-vs-old universe context, says old-world copies and guide context layers are refused with 409, and names `oto_guide` for guide layers. It does not explicitly route edits of old-world copies to a specific sibling surface, so the when-to-use-vs-alternative guidance is strong but not fully exhaustive.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources