Skip to main content
Glama
openl-tablets

OpenL MCP Server

Official
by openl-tablets
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
TypeScript
Remote

Replace Entire Table

openl_update_table
DestructiveIdempotent

Replace an entire table's raw source matrix to modify, reorder, or restructure rows while preserving covered cells and spans. Row removal is rejected; use the dedicated row-deletion tool for deletions.

Instructions

Replace the ENTIRE table RawSource matrix with a modified version. Typed table DTOs are intentionally unsupported. Use for modifying, reordering, or structural changes that preserve or add rows; row removal is rejected, so use openl_delete_table_rows with an explicit position/count. Prefer the narrow raw action tools for isolated edits and append_table for additions. Required workflow: call get_table() without styles=true, preserve the complete matrix including covered cells/spans, modify it, then pass the full RawSource object here. Before writing, the tool reads one live row to verify the submitted source is not shorter than the table; this prevents a sliced view from deleting unseen rows even if totalRows was removed. Studio table write APIs cannot change formatting, so cell style is read-only and rejected. The response returns the CURRENT tableId after relocation. The tool reads the table back to trigger recompilation, so openl_project_status reflects the change.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
viewYesFull, non-windowed RawSource structure from openl_get_table() with modifications applied. Send the complete source matrix, not only changed cells; a view carrying totalRows is rejected, and the handler independently rejects a source with fewer rows than the live table.
tableIdYesTable identifier - unique ID assigned by OpenL Studio (e.g., 'calculatePremium_1234'). VOLATILE: derived from the table's location, so it changes when an edit relocates the table (it had no room to grow in place) — use the 'tableId' returned by the latest openl_update_table/openl_append_table response, or refresh via openl_list_tables().
projectIdYesProject ID returned by backend. Use the exact 'projectId' value from openl_list_projects() response without modification or reformatting.
response_formatNoResponse format: 'json' for structured, round-trippable data (default), 'markdown' for human-readable output, 'markdown_concise' for a brief summary (1-2 paragraphs), or 'markdown_detailed' for full details with contextjson

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed7 schema fields changedv1.2.0
    • changedInput schema / properties / response_format / default
      Previous value: -"markdown"New value: +"json"
    • changedInput schema / properties / response_format / description
      Previous value: -"Response format: 'json' for structured data, 'markdown' for human-readable (default), 'markdown_concise' for brief summary (1-2 paragraphs), 'markdown_detailed' for full details with context"New value: +"Response format: 'json' for structured, round-trippable data (default), 'markdown' for human-readable output, 'markdown_concise' for a brief summary (1-2 paragraphs), or 'markdown_detailed' for full details with context"
    • changedInput schema / properties / view / additionalProperties
      Previous value: -{}New value: +false
    • changedInput schema / properties / view / description
      Previous value: -"FULL table structure from get_table() with your modifications applied. MUST include: id, tableType, kind, name, plus type-specific data (rules for SimpleRules, rows for Spreadsheet, fields for Datatype). Keep 'tableType' EXACTLY as get_table() returned it (it is a CASE-SENSITIVE discriminator: Datatype, Spreadsheet, SimpleRules, SmartRules, SimpleSpreadsheet, Vocabulary, Data, Test, SimpleLookup, SmartLookup, RawSource — lowercase is rejected). Do NOT send only the changed fields - send the complete structure. Workflow: 1) currentTable = get_table(), 2) currentTable.rules[0]['Column'] = newValue, 3) update_table(view=currentTable)"New value: +"Full, non-windowed RawSource structure from openl_get_table() with modifications applied. Send the complete source matrix, not only changed cells; a view carrying totalRows is rejected, and the handler independently rejects a source with fewer rows than the live table."
    • addedInput schema / properties / view / properties
      Added value: +{
+  "id": {
+    "description": "Table id; ignored on create and validated against the path on update.",
+    "type": "string"
+  },
+  "kind": {
+    "description": "Informational table kind.",
+    "enum": [
+      "Rules",
+      "Spreadsheet",
+      "Datatype",
+      "Data",
+      "Test",
+      "TBasic",
+      "Column Match",
+      "Method",
+      "Run",
+      "Constants",
+      "Conditions",
+      "Actions",
+      "Returns",
+      "Environment",
+      "Properties",
+      "Other"
+    ],
+    "type": "string"
+  },
+  "messages": {
+    "description": "Read-only diagnostics tolerated when a get response is round-tripped.",
+    "items": {},
+    "type": "array"
+  },
+  "name": {
+    "description": "Table name (a valid Java identifier).",
+    "type": "string"
+  },
+  "pos": {
+    "type": "string"
+  },
+  "source": {
+    "description": "Complete 2D source matrix. Preserve cell positions, covered placeholders, and spans when replacing a table. Remove read-only style objects returned by styles=true; Studio table write APIs cannot change formatting.",
+    "items": {
+      "items": {
+        "additionalProperties": false,
+        "description": "Writable raw cell. Studio exposes style only when reading with styles=true; table write APIs do not support changing style, so style is intentionally rejected.",
+        "properties": {
+          "cell": {
+            "type": "string"
+          },
+          "colspan": {
+            "maximum": 9007199254740991,
+            "minimum": 1,
+            "type": "integer"
+          },
+          "covered": {
+            "type": "boolean"
+          },
+          "rowspan": {
+            "maximum": 9007199254740991,
+            "minimum": 1,
+            "type": "integer"
+          },
+          "value": {}
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "type": "array"
+  },
+  "tableType": {
+    "const": "RawSource",
+    "type": "string"
+  },
+  "totalRows": {
+    "description": "Total row count when the response contains a window.",
+    "maximum": 9007199254740991,
+    "minimum": -9007199254740991,
+    "type": "integer"
+  }
+}
    • removedInput schema / properties / view / propertyNames
      Removed value: -{
-  "type": "string"
-}
    • addedInput schema / properties / view / required
      Added value: +[
+  "tableType",
+  "source"
+]
  2. Changed2 schema fields changedv1.1.0
    • changedInput schema / properties / tableId / description
      Previous value: -"Table identifier - unique ID assigned by OpenL Studio when table is created (e.g., 'calculatePremium_1234')"New value: +"Table identifier - unique ID assigned by OpenL Studio (e.g., 'calculatePremium_1234'). VOLATILE: derived from the table's location, so it changes when an edit relocates the table (it had no room to grow in place) — use the 'tableId' returned by the latest openl_update_table/openl_append_table response, or refresh via openl_list_tables()."
    • changedInput schema / properties / view / description
      Previous value: -"FULL table structure from get_table() with your modifications applied. MUST include: id, tableType, kind, name, plus type-specific data (rules for SimpleRules, rows for Spreadsheet, fields for Datatype). Do NOT send only the changed fields - send the complete structure. Workflow: 1) currentTable = get_table(), 2) currentTable.rules[0]['Column'] = newValue, 3) update_table(view=currentTable)"New value: +"FULL table structure from get_table() with your modifications applied. MUST include: id, tableType, kind, name, plus type-specific data (rules for SimpleRules, rows for Spreadsheet, fields for Datatype). Keep 'tableType' EXACTLY as get_table() returned it (it is a CASE-SENSITIVE discriminator: Datatype, Spreadsheet, SimpleRules, SmartRules, SimpleSpreadsheet, Vocabulary, Data, Test, SimpleLookup, SmartLookup, RawSource — lowercase is rejected). Do NOT send only the changed fields - send the complete structure. Workflow: 1) currentTable = get_table(), 2) currentTable.rules[0]['Column'] = newValue, 3) update_table(view=currentTable)"
  3. First observedv0.0.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations (destructiveHint, idempotentHint, openWorldHint) are substantially augmented, not contradicted: the description discloses the pre-write verification read, rejection of row removal and style, the volatile tableId relocation behavior, and the read-back that triggers recompilation affecting openl_project_status. This contextualizes the destructiveHint rather than merely repeating it.

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?

Every sentence carries distinct information and purpose is front-loaded, but the description is dense and slightly overlaps schema content (e.g., style read-only rejection is also documented in the source items schema). The length is justified by the tool's risk profile and complexity, though a bit of tightening is possible.

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 high-complexity, destructive whole-table replacement with no output schema, the description covers: what to send, what is rejected (row removal, style, typed DTOs, windows), the safety verification mechanism, the critical volatile return (CURRENT tableId after relocation), and the recompilation side effect. Nothing an agent needs to call it safely is missing.

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% with rich per-property docs, so baseline is 3. The description adds a concrete construction recipe for the complex view/source parameter (call get_table without styles=true, preserve covered cells and spans, modify, pass the full RawSource) and explains why the source cannot be shorter than the live table, which goes modestly beyond the schema's static descriptions.

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?

Opens with a specific verb+resource: 'Replace the ENTIRE table RawSource matrix with a modified version.' It distinguishes itself from siblings by stating what it is for (modifying, reordering, structural changes) and what it is not for (row removal → openl_delete_table_rows; isolated edits → narrow raw action tools; additions → append_table). An agent can select it correctly without inspecting sibling schemas.

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?

Explicitly states when to use (modifying/reordering/structural changes that preserve or add rows), when not to (row removal is rejected), and names concrete alternatives (openl_delete_table_rows, narrow raw action tools, append_table). It also mandates a required workflow (get_table without styles=true → preserve matrix → modify → pass full RawSource), leaving no ambiguity about prerequisites or ordering.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/openl-tablets/openl-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server