Skip to main content
Glama

Create Board

create_board

Create a fresh board in ONE call — optionally pre-filled with content, auto-laid-out, and/or PIN-locked at create time. Mirrors the extended POST /api/boards REST body exactly (same server-side implementation). With no arguments it returns a blank draw board; mode: 'todo' (+ optional template) seeds a kanban board. content imports initial items atomically: everything is validated FIRST and the board is created only if every item passes — on any invalid item you get a structured error naming its kind + index and NOTHING is created. autolayout: true (draw mode) fills in x/y for texts/images that omit them (deterministic masonry grid; explicit coordinates are never touched). lock: 'write'|'all' locks the board atomically with creation and returns the plaintext access_key ONCE — there is no recovery. The response's imported counts confirm what was created, ids returns the server-minted item ids per kind in the order you supplied them (index i of ids.texts is the id created for content.texts[i]; ids.columns is empty when the columns came from the template seed, and lanes have no id — they are keyed by board + lane index), and embed_url (the ?embed=1#<id> iframe view) is returned for any board readable without a key — it is omitted for lock:'all' boards, whose embed frame can't read the board anonymously. Prefer this over open_board + N per-item calls when you are building a whole board from scratch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
lockNoPIN-lock the board atomically at create time; the plaintext key is returned ONCE as `access_key`.
modeNoBoard mode. Defaults to 'draw'.
authorNoAuthor tag stamped on every created item (e.g. 'ai:plai'). Defaults to 'ai:import'.
contentNoInitial board content, applied atomically at create time. Draw mode: `texts` [{x?, y?, content, color?, width?, postit?, diagram?, kind?, author?, sourceId?}], `lines` [{points, color?, anchors?, author?}] (alias `strokes`), `images` [{x?, y?, dataUrl, width, height, author?, sourceId?}]. Todo mode: `columns` [{title, lane?, color?, author?}] (array order = sort order), `tasks` [{columnIndex, name, description?, due_date?, priority?, assignee?, done?, color?, author?}] (columnIndex indexes into content.columns, or into the template-seeded columns when content.columns is empty), `lanes` [{lane, title, author?}], `colWidth`. Every item's optional `author` is its CREATOR tag (same 1-80 char [A-Za-z0-9:_-.] rule as elsewhere) and is never rewritten later — omit it to inherit the top-level `author`, or set it per item to preserve the original authorship when restoring somebody else's board. Item ids are ALWAYS minted server-side and returned in `ids`; you cannot choose them. To keep anchored strokes, give a text/image an optional `sourceId` (unique string, <=128 chars, write-only — never stored, never the row id) and reference it from `lines[].anchors.start.id` / `.end.id`: matching ids are rewritten to the minted id, unmatched ids are left as-is and render as a free stroke end. Kanban structures with a non-todo mode (or draw items with mode 'todo') are rejected with `content_mode_mismatch`. The combined input arrays may contain at most 2550 entries. At most 10 lane-title entries are accepted, every title must reference a lane used by a created column, and each lane index may be named AT MOST ONCE — a second entry for the same lane is rejected (naming that second entry's index) instead of collapsing last-write-wins, which would overwrite the first entry's author. `tasks[].done` must be a real boolean (or omitted/null for not-done): a truthy stand-in such as the string "false" is rejected rather than coerced, so a card is never imported as completed by accident. Standard per-board quotas also apply, and the 5 MB request-body cap is the real ceiling for image-heavy imports. A valid X-Import-Token selects higher REST/MCP and board-create rate tiers, but never changes these content limits.
templateNoStarter column set when mode is 'todo' and content.columns is empty/absent. Defaults to 'kanban'.
autolayoutNoDraw mode only: fill x/y for texts/images that omit them (deterministic masonry). Without it, items missing coordinates are rejected. No-op in todo mode.

TDQS

A4.6/5.0
Behavior4/5

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

The description discloses important behavioral traits like atomic validation, deterministic autolayout, one-time only key recovery, and unmapped content rejection. Given annotations already indicate readOnlyHint=false and openWorldHint=true, the description adds critical details about atomicity and failure modes, though could have mentioned any rate limits or side effects beyond what is stated.

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?

The description is lengthy but well-structured, front-loading the main features and then detailing parameters. It is comprehensive but each sentence adds value, covering atomicity, mode-specific behavior, locking, and import details. Slightly dense but justified for the complexity.

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?

Given the tool's complexity (nested objects, enums, no output schema), the description is remarkably complete. It explains return fields like `imported`, `ids`, `embed_url`, and the nuances of `ids.columns` and lanes. It also covers quotas, request-body limit, and auth tokens. This fills gaps left by the schema and annotations.

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 baseline is 3. However, the description adds significant meaning: explains how content and mode interact, the semantics of author inheritance, sourceId handling, templates, and validation rules. It clarifies edge cases like atomic import and key recovery.

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 clearly states the tool creates a board in a single call with options for content, layout, and locking. It distinguishes itself from sibling tools like open_board and other item-level operations by explicitly saying to prefer this when building a whole board from scratch.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

It provides extensive guidance on when to use this tool vs alternatives, explicitly stating to prefer it over open_board + N per-item calls for building from scratch. Also describes conditions for lock and mode scenarios, and clarifies that unmapped content is rejected.

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.

TDQS

A4.1/5.0
Disambiguation5/5

Each tool targets a distinct resource and action: canvas items (text, image, stroke, link), kanban elements (tasks, columns, lanes), and board-level operations (create, open, preview). Even the two move tools are clearly separated: move for board items and move_task for kanban cards. Descriptions explicitly disambiguate potential overlaps (e.g., add_link vs add_text).

Naming Consistency4/5

Tool names overwhelmingly follow a verb_noun snake_case pattern (add_image, create_column, delete_task, update_task). Minor deviations: 'erase' and 'move' are single-word verbs lacking an explicit object, and 'move' could be confused with 'move_task' without descriptions. Overall the pattern is highly predictable.

Tool Count4/5

25 tools is at the high end but justified by the dual-mode scope (freeform whiteboard and kanban board). Each cluster has a coherent set covering create, read, update, delete, and specialized operations (bulk creation, export, querying, waiting for updates). Slightly heavy but well-scoped.

Completeness4/5

Core workflows for both whiteboard and kanban are covered: CRUD for text, images, tasks, columns, plus preview, export, bulk creation, and filtering. Minor gaps exist: no board rename/delete, no image resize after creation, and no bulk erase, but these can be worked around.