Lucius

Run Test Plan

run_test_plan

Execute an existing test plan by its ID to start a launch and receive a summary with source plan context. If the launch is unwanted, remove it later with delete_launch.

Instructions

Start a launch from an existing Test Plan.

Runs the selected test plan by its ID and returns the created launch as a compact mutation summary enriched with the source plan context. Starting a launch is reversible: use delete_launch to remove it when unwanted.

Input Schema

TableJSON Schema

Name	Required	Description
`tags`	No	Optional list of tags.
`links`	No	Optional list of external links (name, url, type).
`issues`	No	Optional list of issue dictionaries.
`plan_id`	Yes	ID of the test plan to run
`launch_name`	Yes	Name for the launch started from the plan
`output_format`	No	Output format: 'json' (default) or 'plain'.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No
`url`	No
`name`	No
`closed`	No
`plan_id`	No	Source test plan ID for the started launch.
`external`	No
`autoclose`	No
`operation`	No
`project_id`	No
`created_date`	No
`new_defects_count`	No
`last_modified_date`	No
`known_defects_count`	No
`manual_execution_guidance`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv0.15.7Sep 22, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already indicate mutation (readOnlyHint false). The description adds that the mutation is reversible via delete_launch and that the output is a 'compact mutation summary' – this explains side effects and return format, which is useful beyond the schema.

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?

Two concise sentences without fluff. The primary purpose is front-loaded, and the second sentence adds relevant behavioral notes. No wasted words.

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?

The description covers the purpose, side effects, and output nature. Combined with a full schema and output schema, it gives enough for an agent to invoke it. However, it lacks guidance on when to prefer this over related launch tools, leaving some contextual gap.

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?

The input schema already documents all 6 parameters with high coverage (100%). The description mentions the plan ID and launch name implicitly but adds no extra meaning about parameter formats, defaults, or constraints beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Start a launch') and resource ('existing Test Plan'), and clarifies it runs a plan by ID. The action is distinct from manual session startup or generic launch creation, though it doesn't explicitly name siblings.

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?

Gives no guidance on when to use this tool versus alternatives like create_launch or start_manual_test_session. Only provides post-hoc reversibility advice, not selection criteria.

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

Deploy Server