llm-migrate

Overview Schema Source Related Servers Discussions Admin

Start Migration

start_migration

Start a guided migration run by matching source and target models, creating a workspace, and returning precise next steps, with candidate options when identifiers need confirmation.

Instructions

Start a guided migration run; the preferred entry point for a full migration.

Matches both models against the local registry first (tolerating vague or platform-decorated identifiers). If either identifier needs confirmation, nothing is written and the result carries candidates to show the user. Otherwise the run workspace is created (default <application>/.llm-migrate/runs/<run-id>/, or output_dir when given), a bounded research request is written only when knowledge is missing or stale, and next_steps says exactly which tools to call next.

Input Schema

TableJSON Schema

Name	Required	Default
`as_of`	No
`run_id`	No
`source`	Yes
`target`	Yes
`research`	No	auto
`output_dir`	No
`prompt_sources`	No
`source_endpoint`	No
`source_platform`	No
`target_endpoint`	No
`target_platform`	No
`application_path`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv1.3.0Sep 19, 2026

addedInput schema / properties / prompt_sources

Added value: +{
+  "anyOf": [
+    {
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

Addedv1.2.0Sep 16, 2026

TDQS

A4.4/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does well: it discloses that nothing is written when identifiers need confirmation, that a workspace is created otherwise, that research is written only when missing or stale, and that the result includes candidates or next_steps. This gives an agent a clear model of side effects and conditional behavior.

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?

Three sentences, front-loaded with the tool's purpose, then conditional behavior, then side effects and next-step guidance. Every sentence adds substantive information and there is no filler.

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 complex, annotation-free tool with 12 parameters and zero schema descriptions, the description covers the core workflow and side effects very well. It is not completely exhaustive because advanced parameters are left unexplained, but the behavioral flow is detailed enough for an agent to make a reasonable first invocation.

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 0%, so the description must compensate. It does add meaning for source/target as model identifiers, application_path in the workspace path, output_dir, and research to some extent. But many parameters (as_of, run_id, prompt_sources, source_endpoint, target_platform, etc.) remain unexplained, leaving the agent to infer from names alone.

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 opens with a specific verb and resource: 'Start a guided migration run' and immediately positions the tool as 'the preferred entry point for a full migration.' This clearly separates it from sibling tools that generate plans, research requests, or finalize migrations, even though no sibling is named explicitly.

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?

The description gives clear usage context: use this when starting a full migration. It also explains the conditional flow and says next_steps will name the tools to call next. However, it does not explicitly state when NOT to use this tool or name alternative entry points.

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