Skip to main content
Glama

JobMojito

by com.jobmojito
OverviewDiscussionsAdmin

Check and preview a report definition

preview_report
Read-onlyIdempotent

[Reports] Validate a report definition against the catalogue and run it without saving anything. Use it before create_report / update_report: a block that is wrong comes back with ok=false and an error naming the field and the valid ids.

Validates a report definition against the catalogue and runs it, without storing anything. Use it to check a definition before create_report or update_report. A 422 names the block and field that is wrong and lists the valid ids.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
filtersNo
block_idNoRun only this block.
definitionYesA custom report: report-wide filters and up to 12 blocks. Read report-catalog first for the dataset, field and measure ids.
merchant_idNoOptional merchant to act on. Admins and sub-merchant operators only; other callers always use their token's merchant.
conversation_idNoPass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
titleNo
blocksYes
filtersYesThe filters the blocks ran with (report defaults, then your saved filters, then the ones you passed).
versionNo
report_idNo
_mcp_instructionsNoServer-issued metadata for this conversation.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / definition / properties / filters / properties / interview_ids / description
      Previous value: -"Only these interviews (interview ids from list_interviews). Empty or missing = all."New value: +"Interviews to show (interview ids from list_interviews), combined with the other picks by OR. Nothing picked = all."
    • changedInput schema / properties / definition / properties / filters / properties / position_ids / description
      Previous value: -"Only these positions (position ids from list_interviews). Empty or missing = all."New value: +"Positions to show (position ids from list_interviews). position_ids, interview_ids and without_position are one pick list: a row shows when it belongs to ANY pick. Nothing picked = all."
    • addedInput schema / properties / definition / properties / filters / properties / without_position
      Added value: +{
+  "description": "Also pick interviews that are not part of any position (stand-alone interviews, and coaching sessions). Combined with the other picks by OR.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}
    • changedInput schema / properties / filters / allOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "description": "Filters for every block of the report. Each viewer can override them for themselves.",
-    "properties": {
-      "include_test": {
-        "description": "Include test runs. Default false.",
-        "type": [
-          "boolean",
-          "null"
-        ]
-      },
-      "interview_ids": {
-        "description": "Only these interviews (interview ids from list_interviews). Empty or missing = all.",
-        "items": {
-          "format": "uuid",
-          "type": "string"
-        },
-        "maxItems": 200,
-        "type": [
-          "array",
-          "null"
-        ]
-      },
-      "period": {
-        "anyOf": [
-          {
-            "additionalProperties": false,
-            "properties": {
-              "preset": {
-                "enum": [
-                  "last_7_days",
-                  "last_30_days",
-                  "last_90_days",
-                  "this_month",
-                  "last_month",
-                  "this_quarter",
-                  "last_quarter",
-                  "this_year",
-                  "last_year",
-                  "all_time",
-                  null
-                ],
-                "type": [
-                  "string",
-                  "null"
-                ]
-              }
-            },
-            "required": [
-              "preset"
-            ],
-            "type": "object"
-          },
-          {
-            "additionalProperties": false,
-            "properties": {
-              "from": {
-                "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
-                "type": [
-                  "string",
-                  "null"
-                ]
-              },
-              "to": {
-                "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
-                "type": [
-                  "string",
-                  "null"
-                ]
-              }
-            },
-            "required": [
-              "from",
-              "to"
-            ],
-            "type": "object"
-          }
-        ],
-        "description": "Either a preset, or from and to dates (YYYY-MM-DD, both inclusive, UTC). Default: last_30_days.",
-        "example": {
-          "preset": "last_30_days"
-        }
-      },
-      "position_ids": {
-        "description": "Only these positions (position ids from list_interviews). Empty or missing = all.",
-        "items": {
-          "format": "uuid",
-          "type": "string"
-        },
-        "maxItems": 200,
-        "type": [
-          "array",
-          "null"
-        ]
-      }
-    },
-    "type": "object"
-  },
-  {
-    "description": "Applied on top of definition.filters."
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "description": "Filters for every block of the report. Each viewer can override them for themselves.",
+    "properties": {
+      "include_test": {
+        "description": "Include test runs. Default false.",
+        "type": [
+          "boolean",
+          "null"
+        ]
+      },
+      "interview_ids": {
+        "description": "Interviews to show (interview ids from list_interviews), combined with the other picks by OR. Nothing picked = all.",
+        "items": {
+          "format": "uuid",
+          "type": "string"
+        },
+        "maxItems": 200,
+        "type": [
+          "array",
+          "null"
+        ]
+      },
+      "period": {
+        "anyOf": [
+          {
+            "additionalProperties": false,
+            "properties": {
+              "preset": {
+                "enum": [
+                  "last_7_days",
+                  "last_30_days",
+                  "last_90_days",
+                  "this_month",
+                  "last_month",
+                  "this_quarter",
+                  "last_quarter",
+                  "this_year",
+                  "last_year",
+                  "all_time",
+                  null
+                ],
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "required": [
+              "preset"
+            ],
+            "type": "object"
+          },
+          {
+            "additionalProperties": false,
+            "properties": {
+              "from": {
+                "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              },
+              "to": {
+                "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
+                "type": [
+                  "string",
+                  "null"
+                ]
+              }
+            },
+            "required": [
+              "from",
+              "to"
+            ],
+            "type": "object"
+          }
+        ],
+        "description": "Either a preset, or from and to dates (YYYY-MM-DD, both inclusive, UTC). Default: last_30_days.",
+        "example": {
+          "preset": "last_30_days"
+        }
+      },
+      "position_ids": {
+        "description": "Positions to show (position ids from list_interviews). position_ids, interview_ids and without_position are one pick list: a row shows when it belongs to ANY pick. Nothing picked = all.",
+        "items": {
+          "format": "uuid",
+          "type": "string"
+        },
+        "maxItems": 200,
+        "type": [
+          "array",
+          "null"
+        ]
+      },
+      "without_position": {
+        "description": "Also pick interviews that are not part of any position (stand-alone interviews, and coaching sessions). Combined with the other picks by OR.",
+        "type": [
+          "boolean",
+          "null"
+        ]
+      }
+    },
+    "type": "object"
+  },
+  {
+    "description": "Applied on top of definition.filters."
+  }
+]
  2. Added

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds real value beyond them: nothing is persisted, validation is against the catalogue, and failure returns ok=false / a 422 naming the offending block and field plus the valid ids. Minor inconsistency in presenting the failure as both 'ok=false' and 'a 422', but not a contradiction of the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The lead sentence is front-loaded and useful, but the second paragraph is a near-verbatim restatement of the first (validate against catalogue, run, nothing stored, use before create/update, error names the field). Roughly half the text earns no new information, which is a clear structural waste even though the total length is modest.

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?

With an output schema present, the description needn't explain return values, and annotations cover the safety profile; combined with the purpose, the pre-flight guidance and the error semantics, an agent has enough to call it correctly. It could still mention that the definition's dataset/field/measure ids must come from the catalogue, which lives only in the nested schema description.

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 description coverage is 80% and the nested definition schema is heavily self-documented (block types, measures, filters, grain), so the baseline is 3. The description adds no parameter-level meaning — it never mentions block_id (run a single block), merchant_id scoping, or the required conversation_id handshake, all of which are only explained in the schema.

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 states a specific verb+resource combination — validate a report definition and run it without saving anything — and explicitly frames it as a pre-flight step ahead of create_report / update_report. An agent can distinguish it from the other report siblings (create_report, update_report) without opening a schema.

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 gives a clear when-to-use rule: 'Use it before create_report / update_report', which is exactly the decision an agent faces when it has a candidate definition. It does not, however, state when NOT to use it (e.g. to read an already-saved report, where get_report/run_report would apply), so the guidance stops just short of full routing.

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

All JobMojito 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