mcp-creatio

Remove system operation grants

delete-admin-operation-grantee

DestructiveIdempotent

Delete admin operation grant rows by ID to remove explicit allow/deny for users or roles, leaving the operation neither allowed nor denied. Use set-admin-operation-grantee to switch between allow and deny.

Instructions

Delete grant rows by id, so the operation is neither allowed nor denied explicitly for those users/roles. To switch allow ↔ deny use set-admin-operation-grantee.

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": {
      "ids": "<ids>"
    },
    "name": "delete-admin-operation-grantee"
  }
}

Input Schema

Name	Required	Description	Default
`ids`	Yes	Ids of SysAdminOperationGrantee rows (read them by SysAdminOperationId and/or SysAdminUnitId).

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.8.0Oct 25, 2026

changedInput schema / properties / ids / description

Previous value: -"List of SysAdminOperationGrantee row Ids to delete. Look them up via `read` on `SysAdminOperationGrantee` filtered by `SysAdminOperationId` and/or `SysAdminUnitId`."New value: +"Ids of SysAdminOperationGrantee rows (read them by SysAdminOperationId and/or SysAdminUnitId)."

First observedv0.6.5Jun 28, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds genuine value beyond them by explaining the resulting permission semantics (grant falls back to neither allowed nor denied), which annotations cannot convey. It doesn't discuss whether deleted rows can be recreated or what happens on missing ids, but idempotentHint covers the latter.

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 short sentences, front-loaded with the action and effect, followed by the sibling redirect. Every clause 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 single-parameter destructive tool with rich annotations and a fully documented schema, the description covers effect, alternative, and scope. Remaining gaps (irreversibility, behavior on missing ids) are already covered by destructiveHint and idempotentHint.

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 description coverage is 100%, and the ids parameter schema already explains format, minimum count, and where to read the ids from. The description only echoes 'by id', adding nothing the schema doesn't state. Baseline 3 is appropriate.

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 (Delete) and resource (grant rows) plus the precise semantic outcome: the operation becomes neither allowed nor denied for those users/roles. This distinguishes it clearly from set-admin-operation-grantee, which the description explicitly names.

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?

Explicitly routes the agent to set-admin-operation-grantee for the allow ↔ deny switch case, which is the most likely confusable sibling. It doesn't address other edge cases (e.g., deleting a nonexistent id, or removing the user entirely), but the primary alternative is disambiguated.

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