Skip to main content
Glama
Sign In

Krusgraph

by com.krusgraph
OverviewDiscussions(1)Admin

Check the plan against the data

validate_plan
Read-only

Checks the plan against the rows: is each key unique, non-null, how many references find no target (orphans). Requires workspace and source; keys, confirmed as in plan_backend. Returns JSON counts, no row values: failing checks in full, passing as totals. Read-only. create_backend does not run it. Errors: {error, kind, hint}.

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": {
      "workspace": "<workspace>",
      "source": "<source>"
    },
    "name": "validate_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysNoPrimary keys replacing the inferred ones. Default: inferred. Example: {"order_items": ["order_id", "line_no"]}.
fixesNotrue: a fix per finding; applies nothing.
detailNo"summary" (default) or "full" (every check).summary
reviewNoWith fixes: a review_plan file.
schemaNoSchema in the source. Default "dbo".dbo
sourceYesLakehouse, warehouse or SQL database, name or id.
tablesNoTable names or globs to show. Default all. Example: ["sales_*"].
profileNotrue adds per column of the checked tables: NULL share, distinct count, number min/max below/above zero; {"numbers": [lo, hi], "dates": [from, to]} states ranges. One query per table within max_items; never values. Default false.
sql_sumsNotrue also reads the SQL views' definitions (no rows) and lists views that SUM a header amount after joining its line table, and views it could not read. Default false.
confirmedNoRelationships the user confirmed, added to the plan. Default none. Example: [{"source": "orders", "source_cols": ["ship_to_id"], "target": "addresses", "target_cols": ["address_id"]}].
max_itemsNoCap on counting queries (one per key and relationship), 1–200. Default 60.
workspaceYesFabric workspace, name or id.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / fixes
      Added value: +{
+  "default": false,
+  "description": "true: a fix per finding; applies nothing.",
+  "title": "Fixes",
+  "type": "boolean"
+}
    • addedInput schema / properties / review
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "With fixes: a review_plan file.",
+  "title": "Review"
+}
    • addedInput schema / properties / tables
      Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Table names or globs to show. Default all. Example: [\"sales_*\"].",
+  "title": "Tables"
+}
  2. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "properties": {
-    "result": {
-      "title": "Result",
-      "type": "string"
-    }
-  },
-  "required": [
-    "result"
-  ],
-  "title": "validate_planOutput",
-  "type": "object"
-}New value: +null
  3. Changed2 schema fields changed
    • addedInput schema / properties / profile
      Added value: +{
+  "anyOf": [
+    {
+      "type": "boolean"
+    },
+    {
+      "additionalProperties": true,
+      "type": "object"
+    }
+  ],
+  "default": false,
+  "description": "true adds per column of the checked tables: NULL share, distinct count, number min/max below/above zero; {\"numbers\": [lo, hi], \"dates\": [from, to]} states ranges. One query per table within max_items; never values. Default false.",
+  "title": "Profile"
+}
    • addedInput schema / properties / sql_sums
      Added value: +{
+  "default": false,
+  "description": "true also reads the SQL views' definitions (no rows) and lists views that SUM a header amount after joining its line table, and views it could not read. Default false.",
+  "title": "Sql Sums",
+  "type": "boolean"
+}
  4. Changed1 schema field changed
    • addedInput schema / properties / detail
      Added value: +{
+  "default": "summary",
+  "description": "\"summary\" (default) or \"full\" (every check).",
+  "title": "Detail",
+  "type": "string"
+}
  5. Changed6 schema fields changed
    • addedInput schema / properties / confirmed / description
      Added value: +"Relationships the user confirmed, added to the plan. Default none. Example: [{\"source\": \"orders\", \"source_cols\": [\"ship_to_id\"], \"target\": \"addresses\", \"target_cols\": [\"address_id\"]}]."
    • addedInput schema / properties / keys / description
      Added value: +"Primary keys replacing the inferred ones. Default: inferred. Example: {\"order_items\": [\"order_id\", \"line_no\"]}."
    • addedInput schema / properties / max_items / description
      Added value: +"Cap on counting queries (one per key and relationship), 1–200. Default 60."
    • addedInput schema / properties / schema / description
      Added value: +"Schema in the source. Default \"dbo\"."
    • addedInput schema / properties / source / description
      Added value: +"Lakehouse, warehouse or SQL database, name or id."
    • addedInput schema / properties / workspace / description
      Added value: +"Fabric workspace, name or id."
  6. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and destructiveHint=false, and the description reinforces this with 'Read-only'. It adds real value beyond the annotations: output shape ('JSON counts, no row values: failing checks in full, passing as totals') and an error envelope '{error, kind, hint}', which matters since there is no output schema.

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?

Purpose is front-loaded in the first clause and the remaining sentences each carry distinct information (requirements, output shape, safety, error format) with no filler. Some phrasing is over-compressed to the point of obscurity ('keys, confirmed as in plan_backend'), which costs a bit of clarity.

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?

For a 12-parameter tool with no output schema, the description covers what is needed: prerequisites, the checks run, that no row values are returned, the summary/full distinction, and the error format. What a 'plan' is and where it originates is only implied via the plan_backend reference.

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

Parameters3/5

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

Schema coverage is 100%, so parameters are already documented in the schema; the description only cross-references where 'keys' and 'confirmed' come from (plan_backend), which is a small but genuine addition. It adds no meaning for the other ten parameters, so the baseline of 3 is correct.

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 names a specific verb and resource ('Checks the plan against the rows') and enumerates the actual checks performed: key uniqueness, non-null, and orphan reference counts. It also distinguishes itself from the nearest sibling by noting 'create_backend does not run it', so an agent knows validation is a separate step.

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?

It states prerequisites (workspace and source required) and clarifies the workflow relationship with plan_backend ('keys, confirmed as in plan_backend') and create_backend (which does not run it). It stops short of naming the alternative for acting on findings (review_plan / fixes), so the when-not guidance is implied rather than explicit.

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

All Krusgraph 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