mcp-creatio

List entities

list-entities

Read-only

List Creatio entity names and filter by search term to find the right object schema before describing or querying it.

Instructions

Entity (object schema) names available to this server — 1000+ in all, so pass search (e.g. "invoice" → Invoice, InvoiceProduct, …). To find an entity by meaning prefer dataforge-similar-tables or global-search when they are in your tool list. Response: { results: [names] }. Then describe-entity.

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": "list-entities"
  }
}

Input Schema

Name	Required	Description	Default
`search`	No	Part of the name, case-insensitive (e.g. "invoice"). Omit for all names.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.8.0Oct 25, 2026

addedInput schema / properties / search

Added value: +{
+  "description": "Part of the name, case-insensitive (e.g. \"invoice\"). Omit for all names.",
+  "minLength": 1,
+  "type": "string"
+}

First observedv0.6.5Jun 28, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds context the annotations don't: the ~1000+ namespace size (a reason pagination/truncation or scanning may be impractical) and the response envelope { results: [names] }. It doesn't discuss ordering, limits, or whether all names are always returned, which keeps it below a 5.

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 resource and scale, then the search example, then alternatives, response shape, and next step — every clause carries information. The telegraphic, fragment-style phrasing ("Then describe-entity.") is dense but still parseable.

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?

With one optional parameter, full schema coverage, and no output schema, the description supplies the missing return shape ({ results: [names] }) and a clear next action. Only edge behavior (ordering, truncation at 1000+ results) is left unexplained.

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?

The schema already documents `search` at 100% coverage (substring, case-insensitive, omit for all names), so the baseline is 3. The description's concrete example ("invoice" → Invoice, InvoiceProduct, …) and the mention of 1000+ names reinforce why filtering matters, but add little syntactic meaning beyond the schema.

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 the specific resource (entity/object schema names available to this server) and the operation (list, optionally filtered). It also names the closest alternatives (dataforge-similar-tables, global-search) so the agent can distinguish this from them without opening the schema.

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?

Explicit conditional guidance: pass `search` because there are 1000+ names, and prefer dataforge-similar-tables or global-search "when they are in your tool list" for meaning-based lookup. It also gives the follow-up step (describe-entity), so the agent knows the full workflow.

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