Skip to main content
Glama
ivanostanin

Lucius

by ivanostanin
OverviewSchemaSourceRelated ServersScoreDiscussionsAdmin
Python
Remote

Start Manual Test Session

start_manual_test_session

Start a manual execution session for a launch by providing its launch ID. Accepts optional project, environment variables, and output format to configure the session.

Instructions

Start a manual execution session for a launch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
launch_idYesLaunch ID (required).
project_idNoOptional override for the default Project ID.
environmentNoOptional environment variables as [{key, value}, ...].
output_formatNoOutput format: 'json' (default) or 'plain'.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
job_idNo
launch_idNo
job_run_idNo
project_idNo
environmentNo
test_session_idNo

Schema Changelog

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

  1. Changed1 schema field changedv0.14.0
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": false,
+  "properties": {
+    "environment": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": false,
+            "description": "A string key/value pair, for example a manual-session environment entry.",
+            "properties": {
+              "key": {
+                "description": "Variable name.",
+                "title": "Key",
+                "type": "string"
+              },
+              "value": {
+                "description": "Variable value.",
+                "title": "Value",
+                "type": "string"
+              }
+            },
+            "required": [
+              "key",
+              "value"
+            ],
+            "title": "KeyValue",
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Environment"
+    },
+    "job_id": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Job Id"
+    },
+    "job_run_id": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Job Run Id"
+    },
+    "launch_id": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Launch Id"
+    },
+    "project_id": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Project Id"
+    },
+    "test_session_id": {
+      "anyOf": [
+        {
+          "type": "integer"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Test Session Id"
+    }
+  },
+  "title": "StartManualTestSessionOutput",
+  "type": "object"
+}
  2. First observedv0.11.0

TDQS

B3.2/5.0
Behavior2/5

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

With readOnlyHint=false, idempotentHint=false, destructiveHint=false, the description carries the burden but only says 'start a session'. It fails to disclose whether this creates a state, requires permissions, or has side effects beyond initiation.

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

Conciseness5/5

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

The description is a single, front-loaded sentence with no unnecessary words. Every word earns its place.

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

Completeness2/5

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

Despite a descriptive output schema, the description lacks context about prerequisites (e.g., launch state), what a 'manual execution session' entails, or how it relates to sibling tools like close_launch or submit_manual_test_results.

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?

All 4 parameters have descriptions in the schema (100% coverage), so the description adds no param info. Baseline 3 is appropriate.

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 'Start a manual execution session for a launch' is a specific verb+resource phrase that clearly states the tool's action. It distinguishes itself from siblings like create_launch or submit_manual_test_results.

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

Usage Guidelines2/5

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

The description provides no guidance on when to use this tool versus alternatives, nor does it mention prerequisites or constraints. For example, it doesn't indicate whether the launch must be open or if this tool should precede submit_manual_test_results.

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/ivanostanin/lucius-mcp'

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