mcp-creatio

Describe an entity

describe-entity

Read-only

Retrieve an entity's columns, types, required fields and key to plan CRM reads or writes without guessing column names. Use it to pick correct fields before building queries or payloads.

Instructions

Columns of one entity ({ entity: "Contact" }) — names, types, required/nullable and its key — to plan a read or a write without guessing column names. Response: { source, entitySet, ... } where source is "dataforge" (richer column details, when DataForge is enabled), "dataservice" or "odata" (the active backend's schema). An unknown entity fails as "unknown_entity:X. Did you mean: …?".

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "describe-entity"
  }
}

Input Schema

Name	Required	Description	Default
`entity`	No	Entity (object schema) name, e.g. "Contact", "Account".
`entitySet`	No	Old name of `entity`; still accepted.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv0.8.0Oct 25, 2026

addedInput schema / properties / entity

Added value: +{
+  "description": "Entity (object schema) name, e.g. \"Contact\", \"Account\".",
+  "minLength": 1,
+  "type": "string"
+}

changedInput schema / properties / entitySet / description

Previous value: -"Entity set name to describe (e.g., Contact, Account). Returns entity type, key fields, and properties with types/nullable. Use this to plan subsequent read/create/update/delete."New value: +"Old name of `entity`; still accepted."

removedInput schema / required
```
Removed value: -[
-  "entitySet"
-]
```

First observedv0.6.5Jun 28, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well past readOnlyHint=true/openWorldHint=false by disclosing that the `source` field varies by backend (dataforge/dataservice/odata) and giving the exact failure shape for an unknown entity, including the did-you-mean suggestion – information unavailable anywhere in the structured fields.

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 what the tool returns and why call it, then response and error details; dense but nearly every clause earns its place. The nested quoting in the example and the parenthetical source list make it slightly harder to scan than ideal.

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?

No output schema exists, and the description compensates by documenting the response envelope (`source`, `entitySet`), its backend-dependent variants, and the error contract – enough for an agent to call it and interpret results without guessing.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents both `entity` and the legacy `entitySet` alias; the description's inline `{ entity: "Contact" }` example adds an illustrative call but no new semantics, and it never explains that `entitySet` is an accepted alias (only the schema does).

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-resource pair (describe one entity's columns) and enumerates the returned details (names, types, required/nullable, key), which cleanly separates it from the sibling `list-entities` that enumerates entities rather than columns.

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?

"to plan a read or a write without guessing column names" gives a clear usage context, but no explicit when-not or named alternative (e.g. use `list-entities` to discover entity names first) is offered.

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