Skip to main content
Glama

Propose a Base view change (create / update / delete / restore)

view_change_request

Propose a Base view change (create / update / delete / restore)

Review is permission-aware, decided server-side: the change merges immediately when your key has write access on the Base's node and lands as a pending ChangeRequest otherwise — check the response's materialized field to see which happened. Pass requireReview to always propose instead of merging. Views are structure, not content — when you are building starter structure (a Base plus the views that make it usable) let it merge so the workspace is not left half-built behind a review queue, exactly as you would for node_create and POST /bases. create needs the BASE id; update / delete / restore need the VIEW id — the endpoint split follows whichever id identifies the target, which this task handles for you. View order is shared by everyone: a new view joins the end, update with position moves one (0 = leftmost), and the leftmost view is what the Base opens on. Every Base keeps at least one view, so deleting its last one is rejected — create the replacement first. A new Base already starts with a default "Grid view" (every record and field): when you are about to add your own views, create the Base with node_create skipDefaultView (REST defaultView: false) so your first view is the one it opens on.

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": {
      "action": "<action>"
    },
    "name": "view_change_request"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoView name (create; or update, to rename it).
slugNoURL slug for the new view, lowercase `a-z`, `0-9` and `-` (create only; fixed afterwards). Omit it to have one derived from the name — `view-<hash>` when the name has no ASCII letters, with `-2`, `-3`… appended if that one is taken.
typeNoView type: `table`, `gallery`, `kanban`, `calendar` or `gantt`.
patchNoThe update as one object (`name`, `type`, `description`, `config`, `position`) — the same keys the separate arguments set. Pass each key one way, not both (update only).
actionYesWhat to do. Choose this before the other arguments.
baseIdNoBase the view belongs to (create only).
configNoView configuration — filters, sorts, visible fields. On update only the keys you pass change; `sorts: []` clears the sort.
viewIdNoTarget view id.
messageNoExplanation for the reviewer.
playbookNoOptional. The playbook you are following, as `kind:nodeId[:key]` from playbooks_search (e.g. `prompt:nod_123:log-visit`). Recorded on the change request so the person can see which playbook produced it.
positionNoMove the view to this 0-based index among the Base's views (update only); the others shift to make room. 0 makes it the view the Base opens on.
autoMergeNoSkip review and apply the change immediately if you have write access. Not a permission override — a changeRequest-level key still gets a pending CR. Default is permission-aware: merge when you can, otherwise propose.
descriptionNoWhat the view is for (create or update).
submittedByNoProducer label recorded on the change.
requireReviewNoAlways propose a pending ChangeRequest, even with write access.
targetSpaceIdNoBusabase space id. Call auth_verify first and ask the user which space to use when more than one is returned.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • changedInput schema / properties / config / description
      Previous value: -"View configuration — filters, sorts, visible fields (create only)."New value: +"View configuration — filters, sorts, visible fields. On update only the keys you pass change; `sorts: []` clears the sort."
    • addedInput schema / properties / description
      Added value: +{
      +  "description": "What the view is for (create or update).",
      +  "type": "string"
      +}
    • changedInput schema / properties / name / description
      Previous value: -"View name (create only)."New value: +"View name (create; or update, to rename it)."
    • changedInput schema / properties / patch / description
      Previous value: -"Changes to apply to the view (update only)."New value: +"The update as one object (`name`, `type`, `description`, `config`, `position`) — the same keys the separate arguments set. Pass each key one way, not both (update only)."
    • addedInput schema / properties / slug
      Added value: +{
      +  "description": "URL slug for the new view, lowercase `a-z`, `0-9` and `-` (create only; fixed afterwards). Omit it to have one derived from the name — `view-<hash>` when the name has no ASCII letters, with `-2`, `-3`… appended if that one is taken.",
      +  "type": "string"
      +}
    • changedInput schema / properties / type / description
      Previous value: -"View type, e.g. `table`, `gallery` (create only)."New value: +"View type: `table`, `gallery`, `kanban`, `calendar` or `gantt`."
  2. Changed1 schema field changed
    • addedInput schema / properties / position
      Added value: +{
      +  "description": "Move the view to this 0-based index among the Base's views (update only); the others shift to make room. 0 makes it the view the Base opens on.",
      +  "minimum": 0,
      +  "type": "number"
      +}
  3. Changed1 schema field changed
    • addedInput schema / properties / playbook
      Added value: +{
      +  "description": "Optional. The playbook you are following, as `kind:nodeId[:key]` from playbooks_search (e.g. `prompt:nod_123:log-visit`). Recorded on the change request so the person can see which playbook produced it.",
      +  "type": "string"
      +}
  4. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: review is permission-aware and decided server-side, the `materialized` response field tells you which path ran, requireReview/autoMerge nuances (including that autoMerge is not a permission override), view order is global with position 0 as the Base's opening view, and the last remaining view cannot be deleted. The annotations only say non-read-only and non-destructive; the description supplies the merge/auth model that actually governs behavior.

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-loads the operation and then the review/merge decision before details, which is the right order for an agent. It is dense and runs long for a 16-parameter tool, with scaffolding advice ("exactly as you would for node_create") that is useful but slightly tangential, keeping it below maximum.

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?

For a 16-parameter mutation tool with no output schema, it covers the pieces an agent would otherwise guess wrong: which id each action needs, what the response signals, ordering side effects, the delete-last-view rejection, and the review escape hatches. Nothing material is missing before a first call.

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 baseline is 3, and the description still adds meaning: baseId is needed for create while viewId is needed for update/delete/restore, and `position` is a 0-based index whose 0 value makes that view the one the Base opens on. It also ties `skipDefaultView` on node_create to the default "Grid view" that would otherwise occupy position 0, which no single parameter schema can express.

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?

"Propose a Base view change (create / update / delete / restore)" states a specific verb set and resource, and the parenthetical enumerates the exact operations. It is distinguishable from field/node siblings by the word "view", but it never names those siblings (base_field_change_request, bases_lifecycle_change_request) so the boundary is inferred from the noun rather than stated.

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 real when-to guidance: let structure changes merge when scaffolding a Base, use requireReview to force a pending ChangeRequest, create the replacement view before deleting the last one, and create the Base with skipDefaultView if you want your own view to be the opening one. It stops short of naming the alternative tools for the read side (bases_list_views) or the state to check afterward (change_request_query / change_requests_get).

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.