Skip to main content
Glama

Dock

by ai.trydock
OverviewDiscussionsAdmin

create_surface

Create a new surface (tab) inside a workspace. kind picks table, doc, html, or files. Optional slug (lowercase kebab-case, 3-64 chars); when omitted the server slugifies name and appends a numeric suffix on collision. Optional columns overrides the default Title/Status/Notes triple for table kinds; ignored for doc and html. html surfaces start with an empty body — write content via update_html. files surfaces start empty; browse them with list_files / get_file / list_recent_files, and add files with upload_file. Editor role required. Emits surface.created so live listeners on the workspace stream see the new tab without a refetch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesSurface kind. `table` for rows + columns, `doc` for TipTap body, `html` for a sandboxed HTML mockup tab, `files` for uploaded files + folders.
nameYesDisplay name shown on the tab. 1-64 chars.
slugYesThe workspace slug. Accepts either the bare slug ('my-workspace') or the org-prefixed form ('my-org/my-workspace') as shown in the dashboard URL; both resolve to the same workspace.
columnsNoOptional initial columns for `table` kind. Same shape as get_workspace_schema returns. Defaults to Title/Status/Notes when omitted.
surface_slugNoOptional URL-friendly slug for the surface (lowercase kebab-case, 3-64 chars). Auto-derived from `name` when omitted.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Surface kind. `table` for rows + columns, `doc` for TipTap body, `html` for a sandboxed HTML mockup tab."New value: +"Surface kind. `table` for rows + columns, `doc` for TipTap body, `html` for a sandboxed HTML mockup tab, `files` for uploaded files + folders."
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "table",
-  "doc",
-  "html"
-]New value: +[
+  "table",
+  "doc",
+  "html",
+  "files"
+]
  2. Changed2 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Surface kind. `table` for rows + columns, `doc` for TipTap body."New value: +"Surface kind. `table` for rows + columns, `doc` for TipTap body, `html` for a sandboxed HTML mockup tab."
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "table",
-  "doc"
-]New value: +[
+  "table",
+  "doc",
+  "html"
+]
  3. Changed3 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Surface kind. `table` for rows + columns, `doc` for TipTap body, `html` for sandboxed HTML/CSS/JS."New value: +"Surface kind. `table` for rows + columns, `doc` for TipTap body."
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "table",
-  "doc",
-  "html"
-]New value: +[
+  "table",
+  "doc"
+]
    • changedInput schema / properties / name / description
      Previous value: -"Display name shown on the tab. 1-64 chars. Make it specific to what the surface holds (e.g. 'Findings', 'Weekly schedule', 'Architecture diagram'). Avoid generic placeholders like 'Notes' or 'Sheet' — those leave every tab in a multi-surface workspace looking the same."New value: +"Display name shown on the tab. 1-64 chars."
  4. Changed3 schema fields changed
    • changedInput schema / properties / kind / description
      Previous value: -"Surface kind. `table` for rows + columns, `doc` for TipTap body."New value: +"Surface kind. `table` for rows + columns, `doc` for TipTap body, `html` for sandboxed HTML/CSS/JS."
    • changedInput schema / properties / kind / enum
      Previous value: -[
-  "table",
-  "doc"
-]New value: +[
+  "table",
+  "doc",
+  "html"
+]
    • changedInput schema / properties / name / description
      Previous value: -"Display name shown on the tab. 1-64 chars."New value: +"Display name shown on the tab. 1-64 chars. Make it specific to what the surface holds (e.g. 'Findings', 'Weekly schedule', 'Architecture diagram'). Avoid generic placeholders like 'Notes' or 'Sheet' — those leave every tab in a multi-surface workspace looking the same."
  5. Changed1 schema field changed
    • changedInput schema / properties / slug / description
      Previous value: -"The workspace slug. Accepts either the bare slug ('my-workspace') or the org-prefixed form ('my-org/my-workspace') as shown in the dashboard URL — both resolve to the same workspace."New value: +"The workspace slug. Accepts either the bare slug ('my-workspace') or the org-prefixed form ('my-org/my-workspace') as shown in the dashboard URL; both resolve to the same workspace."
  6. First observed

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full burden. It discloses the editor role requirement, the automatic slugification with numeric suffix on collision, the kind-specific default behavior (columns ignored for doc/html, html starts empty, files starts empty), and the emission of a 'surface.created' event so live listeners see the new tab. These are meaningful behavioral traits beyond simple 'creates a resource.' It does not describe the return value or reversibility, but for a creation tool this covers the critical operational aspects.

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 longer than typical but well-structured, front-loading the core purpose in the first sentence. Every clause adds relevant information: kind behavior, slug logic, columns semantics, per-kind workflows, permission requirement, and event emission. No filler or redundancy; it earns its length.

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

Completeness4/5

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

Given five parameters, no output schema, and no annotations, the description covers essential context: required role, event behavior, collision semantics, and per-kind specifics. The main gap is the lack of return value information, but without an output schema the description does not have to enumerate the response. Overall, it is sufficiently complete for an agent to invoke correctly.

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 description coverage is 100%, so the baseline is 3. The description adds genuine value beyond the schema: it explains the slug auto-derivation and collision handling that the schema only hints at, clarifies that columns are ignored for non-table kinds, and specifies the exact default columns (Title/Status/Notes). This is substantive semantic enrichment that helps an agent set parameters correctly.

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 opens with a clear verb-resource pairing: 'Create a new surface (tab) inside a workspace.' It also explicitly lists the four supported kinds (table, doc, html, files), which distinguishes it from siblings like create_workspace (different resource) and update_surface (different verb).

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?

The description gives practical usage context: it explains how kind selects behavior, notes that columns only apply to table, and points to follow-up tools (update_html, list_files, upload_file) for post-creation actions. It does not explicitly contrast with update_surface, but the 'create' vs 'update' distinction is implied given the sibling list, and the guidance about per-kind workflows is strong.

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

All Dock 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