Playbook

Apply page operations

apply_page_operations

Destructive

Apply up to 50 page edits to a board's published page in order and ATOMICALLY — the first failure rolls everything back, and the error carries operation_index naming the failing operation. Each operation is { type: add|update|move|delete|reorder, ...} with exactly the arguments of the matching single tool (add_page_element etc., minus organization/token/subboard_token/expected_version_token, which are batch-level); operations in get_page_elements_catalog is the authoritative argument map, and unknown keys are refused. Ids the server mints inside a batch cannot be addressed by later operations of the same batch, so give every new element (and a new section's columns) your own id. Returns the whole document (slots) and one summary per operation. Top-level converged appears only when EVERY operation converged, and never on a batch containing an update. One batch edits one document: the main page, or one nested board's section. Requires modify on the board and page-layout API writes enabled for the workspace — otherwise 403 page_layout_api_disabled, which only Playbook can turn on; retrying does not help. Concurrency: pass the version_token from get_page_layout as expected_version_token; if the page changed since, the call answers 409 stale_document and applies NOTHING — read again, re-decide, re-send. A successful write that sent a token returns the NEW version_token: send that on your next write, because your own write already made the old one stale. Of the 409s only lock_wait_timeout and page_layout_library_locked are safe to repeat unchanged. converged: true in the response means nothing changed (the goal state already held); materialized: true means the page had no stored document and this call saved the template's defaults. Both keys are ABSENT when false. The public page can keep showing the old version for up to an hour after a successful write, so a reload may not show the change.

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": {
      "token": "<token>",
      "operations": "<operations>"
    },
    "name": "apply_page_operations"
  }
}

Input Schema

Name	Required	Description
`token`	Yes	Board token of the published board
`operations`	Yes	The edits, e.g. { type: 'delete', slot_id: 'grid', element_id: '<id from get_page_layout>' }.
`organization`	No	Workspace slug, as returned by list_organizations. Omit it when the account has a single workspace — it is then resolved from your token. Pass it only when the account has several, or when you mean a workspace other than the obvious one.
`subboard_token`	No	Edit a nested board's section of this page instead of the page itself: the `collectionToken` of an entry in get_page_layout's `subboards_settings`. Omit for the main page.
`expected_version_token`	No	The `version_token` from get_page_layout, echoed verbatim to make this write a compare-and-swap. Omit to write unconditionally.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 3, 2026
- removedInput schema / additionalProperties
```
Removed value: -false
```
- changedInput schema / properties / operations / items / additionalProperties
```
Previous value: -trueNew value: +{}
```

Changed3 schema fields changedOct 5, 2026

addedInput schema / additionalProperties
```
Added value: +false
```

removedInput schema / properties / context

Removed value: -{
-  "description": "Explain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): \"Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization.\"",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "token",
-  "operations",
-  "context"
-]New value: +[
+  "token",
+  "operations"
+]

First observedOct 2, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare the mutation/safety profile; the description goes far beyond with atomic rollback semantics, `operation_index` on failure, server-minted ids being unaddressable later in the batch, the 403 `page_layout_api_disabled` dead end, 409 `stale_document` applying nothing, which errors are safe to repeat, and up-to-an-hour public page staleness. This is exactly the operational context annotations cannot carry.

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 atomicity guarantee and every sentence carries non-redundant information, but it is delivered as one dense block covering atomicity, ids, permissions, concurrency, and caching. Slight restructuring (grouping the 403/409/retry material) would aid scanning without cutting content.

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 destructive, non-idempotent batch mutation with no output schema, it covers return shape ('the whole document (slots) and one summary per operation'), the meaning and absence-condition of `converged` and `materialized`, failure behavior, and auth prerequisites. Nothing an agent needs to call it correctly is missing.

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

Parameters5/5

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

Schema coverage is 100%, so baseline would be 3, but the description adds real meaning: `operations` is authoritative via get_page_elements_catalog with unknown keys refused, batch-level exclusion of organization/token/subboard_token/expected_version_token from each operation, and the token-rotation rule that a successful write returns a new `version_token` to send next.

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 with scope: 'Apply up to 50 page edits to a board's published page in order and ATOMICALLY'. It also positions itself against the single-operation siblings by saying each operation takes exactly the arguments of 'the matching single tool (add_page_element etc.)', so an agent can immediately tell batch from single-edit tools.

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 concrete conditions for correct use: one batch edits one document (main page or one nested section via subboard_token), requires `modify` plus page-layout API writes, and pass `expected_version_token` for compare-and-swap. It explains retry policy per 409 code. It never explicitly says when to prefer a single-element tool over a batch, which is the only gap.

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

All Playbook tools Inspect

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

Need Help?