llm-migrate

Overview Schema Source Related Servers Discussions Admin

Submit Adapted Prompt

submit_adapted_prompt

Submit a reviewed prompt adaptation for the target model: validate changes with evidence, or confirm the original unchanged, rejecting cosmetic-only edits.

Instructions

Validate and store one refined prompt for the target model.

Adapt minimally: keep the original wording and structure except where a listed model difference or evidence-linked guidance item requires a change, and cite that evidence in changes. Validation runs on the DECODED runtime prompt values, and a submission whose decoded values equal the original's — or differ only by whitespace or letter case — is rejected: serialization tricks, escapes, quoting and cosmetic edits are never an adaptation. If the prompt needs no change, pass unchanged=true with an EMPTY adapted_prompt (combining it with content is an error) to record a reviewed no-change deliverable; the claim is refused when the prompt's decoded values still reference the source model. Blockers are rejected, and a submission that drops the original's structural sections (XML-like tags or prompt components) is rejected unless allow_restructure is true and the justification is recorded in changes. Accepted prompts are written beneath <run>/output/prompts/ mirroring the application layout, and the rationale/changes appear verbatim in the final migration report.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`changes`	No
`run_dir`	Yes
`rationale`	Yes
`unchanged`	No
`source_path`	Yes
`adapted_prompt`	Yes
`allow_restructure`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv1.3.0Sep 19, 2026
- addedInput schema / properties / allow_restructure
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
- addedInput schema / properties / unchanged
```
Added value: +{
+  "default": false,
+  "type": "boolean"
+}
```
Addedv1.2.0Sep 16, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It thoroughly explains validation on decoded values, rejection of cosmetic edits, handling of unchanged submissions, rejection of blockers and structural drops, output location, and report inclusion. This is exceptionally transparent for a complex tool.

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?

The description is long but every sentence earns its place—it covers validation rules, edge cases, and side effects without fluff. It is front-loaded with the core purpose and then systematically details constraints. The structure is logical and dense, though it could be tightened by removing some redundancy (e.g., repeated emphasis on rejection).

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

Completeness5/5

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

For a tool with no annotations, no parameter descriptions in schema, and significant complexity, the description is remarkably complete. It covers validation criteria, rejection conditions, unchanged handling, structural rules, output destination, and report integration. An agent has everything needed to call it correctly. Return format is not mentioned, but an output schema likely covers that.

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

Parameters4/5

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

Schema coverage is 0%, so the description must explain parameters. It explicitly clarifies `changes`, `unchanged`, `adapted_prompt`, and `allow_restructure`, including the constraint that `unchanged=true` requires an empty `adapted_prompt`. `run_dir`, `source_path`, and `rationale` are not individually described but are inferable from context (output path, source file, and report mention). The critical parameters are well covered, with minor gaps on the obvious ones.

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 'Validate and store one refined prompt for the target model,' which is a specific verb+resource statement. It clearly distinguishes from siblings like submit_adapted_file (for files) and other prompt-analysis tools. The purpose is unambiguous and immediately actionable.

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 provides clear conditions for using the tool: when to pass unchanged=true, when allow_restructure is needed, and what gets rejected. It does not explicitly name alternatives or state 'use this when X, use that when Y,' but the context of a final submission is implied. It gives enough guidance for an agent to decide when to invoke it.

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