LegendKeeper MCP

delete_document

DestructiveIdempotent

Delete a single document (tab) from a LegendKeeper resource after user confirmation; it can be restored later through the API.

Instructions

Delete one document (tab) of a resource. It can be restored with api_request (POST /resources/{id}/docs/{docId}/restore).

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": {
      "resource": "<resource>",
      "document": "<document>"
    },
    "name": "delete_document"
  }
}

Input Schema

Name	Required	Description
`confirm`	No	Must be true. Ask the user before deleting.
`project`	No	Configured project (world) name. Omit to use the default project; see list_projects.
`document`	Yes	Document id or name.
`resource`	Yes	Resource id, or its exact name/alias (case-insensitive).

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.2Oct 17, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=true and openWorldHint=true, so the safety profile is covered. The description earns credit for adding reversibility context the annotations cannot express: the deleted document can be restored via POST /resources/{id}/docs/{docId}/restore. It still does not say what downstream references break or whether the operation is immediate.

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 sentences, zero filler, with the scope constraint (one document/tab) front-loaded and the recovery endpoint compactly parenthesized.

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 destructive mutation with no output schema, the description plus annotations cover the essentials: what it deletes, that it is reversible, and how to reverse it, while confirm semantics live in the schema. Minor gap: no statement of permission requirements or side effects on resources referencing the deleted document.

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 schema itself documents all four parameters including the required confirm=true with a user-consent instruction. The description adds no parameter-level detail beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource, and immediately narrows scope to "one document (tab) of a resource," which distinguishes it from delete_resource. However, it never names the sibling it is adjacent to (delete_resource, update_document) so the differentiation is implicit rather than explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when deletion is appropriate by framing it as a per-document (tab) operation, and it points to a recovery route via api_request restore. It gives no explicit when-not guidance (e.g., use update_document to clear content instead of deleting) and names no alternative tool.

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