Meridian

Record Developer Database Migration

dev_database_migrate

Idempotent

RECORDS the outcome of a database migration YOU (or your agent) ALREADY RAN LOCALLY against your own developer database. Meridian does NOT execute migrations for you. There is no server-side migration runner, and calling this tool never applies any schema change by itself. To actually run a migration, use the Meridian CLI's meridian migrate command locally (it runs npx prisma migrate dev against your proxied developer database and calls this same recording step automatically). Only call this tool yourself if you ran the migration another way (e.g. Prisma directly) and want the run to show up in the same history dev_database_get and the dashboard display.

Takes the app_id returned by apps_list, the exact command you ran, its status (success, failed, or rolled_back), and optional started_at/finished_at (ISO-8601) and output_excerpt (truncated to 5000 characters). IDEMPOTENT: re-reporting the exact same command + started_at for this developer database returns the SAME recorded run (created: false) instead of creating a duplicate: safe to retry after a dropped response.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "app_id": "<app_id>",
      "command": "<command>",
      "status": "<status>"
    },
    "name": "dev_database_migrate"
  }
}

Input Schema

Name	Required	Description
`app_id`	Yes	The app uuid returned by `apps_list`.
`status`	Yes	Outcome of the run: `success`, `failed`, or `rolled_back`.
`command`	Yes	The exact command you ran locally, e.g. `npx prisma migrate dev --name add_orders`.
`started_at`	No	ISO-8601 timestamp the migration run started, if known.
`finished_at`	No	ISO-8601 timestamp the migration run finished, if known.
`output_excerpt`	No	A short excerpt of the command's output, for debugging context. Truncated to 5000 characters.
`organization_id`	No	An organisation uuid or slug. When supplied, `app_id` is resolved within that organisation and may be a slug instead of a uuid, mirroring the Meridian web app.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the annotations, it discloses that invocation performs no schema migration, explains the exact idempotency identity of `command` plus `started_at`, and states that a repeated report returns the same run with `created: false`. It also supports safe retry after a dropped response and documents the 5000-character output-excerpt truncation.

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 front-loads the crucial non-execution warning, then separates invocation guidance from parameter and retry behavior into two readable paragraphs. It is somewhat repetitive in emphasizing that migrations are not executed and restates several schema details, but the length is largely justified by the risk of confusing recording with migration execution.

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 seven-parameter recording tool with no output schema, the description supplies the prerequisite local run, the preferred CLI workflow, direct-use conditions, history integration, side-effect boundaries, and idempotent retry behavior. It also identifies the recorded-run response and `created: false` on duplicates, leaving no significant information needed for correct invocation.

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 already 100%, and much of the second paragraph repeats the schema's parameter formats and allowed status values. It nevertheless adds meaningful cross-parameter semantics by explaining that `command` and `started_at` jointly determine idempotent re-reporting, making `started_at` more significant than its optional schema status alone suggests.

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 opening sentence precisely identifies the operation as recording the outcome of an already-completed local developer-database migration, not performing one. The explicit statements that Meridian has no server-side migration runner and that this tool never applies schema changes resolve the potentially misleading `dev_database_migrate` name.

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

Usage Guidelines5/5

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

It gives an explicit alternative for actually running a migration: use the local Meridian CLI's `meridian migrate` command, which also records the run automatically. It then clearly limits direct tool use to migrations run another way, such as Prisma directly, when the user wants the run included in the history shown by `dev_database_get` and the dashboard.

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

All Meridian tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?