Skip to main content
Glama

RationalBloks

by io.github.rationalbloks

Update Schema

update_schema
Idempotent

Update a project's schema (saves to database, does NOT deploy).

⚠️ CRITICAL: Follow ALL rules from create_project: • FLAT format (no 'fields' nesting) • string: MUST have max_length • decimal: MUST have precision + scale • Use "datetime" NOT "timestamp" • DON'T define: id, created_at, updated_at • NEVER create users/customers/employees tables (use app_users)

⚠️ MIGRATION RULES: • New fields MUST be "required": false OR have "default" value • Cannot add required field without default to existing tables • Safe: {new_field: {type: "string", max_length: 100, required: false}}

WORKFLOW:

  1. Use get_schema to see current schema

  2. Modify following ALL rules

  3. (optional) Call update_schema with dry_run=true to preview the migration first

  4. Call update_schema (saves only)

  5. Call deploy_staging to apply changes

  6. Monitor with get_job_status

DRY RUN: pass dry_run=true to preview what a deploy WOULD change — renames, drops, creates — without saving or deploying anything. The response flags destructive operations (dropped tables/columns) so you can review before applying.

NOTE: Without dry_run this only saves the schema. You MUST call deploy_staging afterwards to apply changes.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
schemaYesNew JSON schema in FLAT format (table_name → field_name → properties). Every field MUST have a 'type' property.
dry_runNoPreview the planned migration (renames/drops/creates) without saving or deploying. Nothing is applied.
project_idYesProject ID (UUID)

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations, it reveals the side-effect boundary (no deployment), dry-run behavior (previews renames/drops/creates without saving), and migration rules such as required fields needing defaults on existing tables. This adds substantial behavioral context that readOnlyHint/destructiveHint/idempotentHint alone do not provide.

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?

Organized into labeled sections with front-loaded warnings and a clear workflow; no fluff and every section earns its place. It is slightly longer than necessary because 'saves only/no deployment' is repeated in several places and dry_run behavior appears in both the schema and the prose.

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 schema-mutation tool with no output schema, it covers prerequisites, validation constraints, safe migration patterns, and downstream deployment steps. The only notable gap is the direct response contract of the normal non-dry-run call, so the agent must infer what update_schema itself returns after saving.

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?

The input schema already documents all three parameters. The description adds critical schema-format constraints: flat format, max_length for strings, precision/scale for decimals, datetime instead of timestamp, forbidden fields, and forbidden table names. It also clarifies that dry_run flags destructive operations, though some dry_run details duplicate the schema description.

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 first sentence names an exact action ('Update a project's schema') and immediately scopes it with 'saves to database, does NOT deploy.' This separates it from deployment/apply tools and clarifies the project-schema context, distinguishing it from graph-schema siblings.

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?

Contains an explicit numbered WORKFLOW: inspect with get_schema, optionally dry-run, update_schema, deploy_staging, and monitor with get_job_status. It also explains when dry_run=true should be used to preview a migration, so the agent knows exactly when to call this tool versus read/deploy siblings.

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

All RationalBloks toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0
Disambiguation4/5

Most tools are clearly differentiated by domain (project vs graph_project) and action (create, get, list, delete). The main ambiguity is get_project vs get_project_info, which both claim to return detailed project information. Otherwise tool boundaries are clear.

Naming Consistency4/5

The server follows a strong verb_noun convention, with parallel naming for graph and non-graph tools (create_project/create_graph_project, deploy_staging/deploy_graph_staging). Minor deviations include bulk_create_graph_nodes and fulltext_search_graph, but patterns remain predictable.

Tool Count2/5

48 tools is a heavy surface, even when accounting for the two parallel product domains (relational and graph). Many tools are near-duplicates across domains, and the count exceeds the 25-tool threshold that feels manageable. It would benefit from consolidation or sub-servers.

Completeness4/5

Both project types have full life-cycle coverage: create, schema management, deployment, rollback, and deletion, plus graph data operations including bulk, search, and traversal. Minor gaps exist, such as no update_graph_relationship and the redundant get_project/get_project_info pair, but agents can accomplish core workflows.

Resources