Spaces by Peakflo

table_create

Create a new data table in the workspace.

Do not use data tables for standard finance objects: vendor, customer, employee, subsidiary, gl_account, expense_category, ledger_entry, invoice, invoice_line, credit_note, payment, bill, bill_line, purchase_order, po_line, receipt_note, receipt_note_line. These are Business Context entity types stored in the standard tables that reports (report_query, e.g. billing_overview) read. Write them with a workflow that uses an entity_write step (batch mode: name, data and externalId as arrays) with that entityType. Use data tables only for other, custom data.

Accepts a table name and an array of column definitions, executes CREATE TABLE in the tenant's workspace PostgreSQL schema, and registers the table in the catalog.

Auto-managed columns (id, created_at, updated_at) are always added — do not include them.

Allowed pgType values: text, integer, bigint, numeric, boolean, timestamptz, date, uuid, jsonb

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": {
      "tableName": "<tableName>"
    },
    "name": "table_create"
  }
}

Input Schema

Name	Required	Description	Default
`columns`	No	JSON array of column definitions. Each entry: {"name":"col","pgType":"text","isNullable":true,"defaultExpr":"now()"}. isNullable defaults to true. defaultExpr is optional.
`tableName`	Yes	Table name — lowercase letters, digits and underscores only, max 63 chars (e.g. "invoices", "ap_lines")

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare the generic readOnly/destructive/openWorld profile, but the description adds real mechanics: the operation runs CREATE TABLE against the tenant workspace PostgreSQL schema and registers the result in the catalog. It also discloses that id, created_at and updated_at are auto-managed and must not be supplied, which materially changes how an agent calls it. Minor omission is what happens on name collision, but this is well beyond the annotation baseline.

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?

Front-loaded with the action, then the routing exclusion, then mechanics, then the type whitelist — a sensible order. The long entity-type enumeration is bulky but functional and cannot be trimmed without losing the routing signal. Slightly dense, though every sentence carries information.

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 schema-mutating tool with no output schema, the description covers the creation mechanics, the type whitelist, the auto-column rule and the entity-type exclusion. The only real gap is what the call returns (table identifier, resulting column set), which an agent may need to chain into table_insert or table_query.

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 100%, so the baseline is 3, and the description earns an upgrade by enumerating the allowed pgType values (text, integer, bigint, numeric, boolean, timestamptz, date, uuid, jsonb) which the schema only hints at via an example. The auto-managed column prohibition further constrains what may go into the columns array. It does not add naming-format or default-expression guidance beyond the schema, keeping it below a 5.

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?

States a specific verb and resource ('Create a new data table in the workspace') and then concretizes the mechanism: executes CREATE TABLE in the tenant's PostgreSQL schema and registers the table in the catalog. That mechanism sentence alone separates it from siblings like dataset_create or graph_create_entity_type.

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?

Gives an explicit when-not clause with an enumerated list of standard finance entity types and names the correct alternative path (a workflow with an entity_write step in batch mode). It closes with a positive scoping rule: 'Use data tables only for other, custom data.' This is about as complete as routing guidance gets.

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

All Spaces by Peakflo tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.