Skip to main content
Glama
Sign In
RPG Maker MZ Authoring MCP

RPG Maker MZ Authoring MCP

by NixonMSilva
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Preview database changes (batch)

database_preview_changes

Preview and validate multiple RPG Maker MZ database and event operations as a single atomic change set before committing, so records and references are checked first.

Instructions

Preview several operations as one atomic change set; the complete resulting state is validated (records, references, reverse references). Operations: create_map_event, update_map_event, delete_map_event, create_event_page, clone_event_page, delete_event_page, update_event_page_settings, reorder_event_pages, update_common_event, create_event_from_template, append_event_blocks, insert_event_blocks, replace_event_block, remove_event_block, move_event_block, replace_event_logic, database_create_record, database_update_record, database_duplicate_record, database_delete_record, database_edit_collection, database_edit_note, database_set_class_curve.

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": {
      "operations": "<operations>"
    },
    "name": "database_preview_changes"
  }
}

Input Schema

NameRequiredDescriptionDefault
applyNoCommit right after a successful preview (non-destructive operations only; needs --allow-write; warnings also need acknowledgeWarnings). Default false = preview only.
operationsYes
allowScriptNotrue ONLY if the user explicitly asked to insert JavaScript (script commands, script conditions/operands, route scripts).
descriptionNoOptional description stored in the transaction log
acknowledgeWarningsNoAccept validation warnings when apply=true. Review them with the user first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations declare readOnlyHint=false and openWorldHint=false, so the safety profile is only partly covered; the description usefully adds that the entire resulting state is validated before anything is committed, which explains the dry-run semantics. It omits what happens to the produced change set afterward (must it be applied via a sibling, does it expire, is it stored?), leaving the mutation lifecycle opaque for a tool that can write when apply=true.

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 sentences, front-loaded with the core action and consequence before the operation catalog. The long op list is dense but every entry is load-bearing because `op` has no enum in the schema; no redundant restatement of the title or parameters.

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

Completeness3/5

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

For a tool that can stage or commit writes across 23 operation types, the description covers validation but not the return value, the fate of the pending change set, or how it hands off to apply_changes/discard_changes. With no output schema and no reverse-reference to the apply/discard siblings, an agent can call it but cannot confidently drive the full workflow.

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 80%, so apply, allowScript, description and acknowledgeWarnings are already documented in the schema. The description's real contribution is enumerating the 23 valid values for the otherwise unconstrained `op` string field ('op': {'type':'string'}), which the schema does not enumerate at all. It adds nothing about the shape of `args` per operation, so it is not fully compensating.

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 and resource ('Preview several operations as one atomic change set') plus the validation scope (records, references, reverse references). The enumerated operation list further pins down the domain. It never names the sibling it differs from (preview_changes, preview_event_changes, database_apply_changes), so differentiation relies on the agent reading the op list.

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

Usage Guidelines3/5

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

'several operations as one atomic change set' implies batch/multi-op usage, and the apply parameter description sketches a preview-then-commit workflow. But there is no explicit when-to-use versus preview_changes / apply_changes / discard_changes, and no statement of when a single-op tool is preferable. Guidance is implied rather than stated.

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

Deploy Server

Other Tools