Skip to main content
Glama

delete_entities

Destructive

Delete multiple documents, files, or folders from an Overleaf project in one call, with path validation and per-item status reporting.

Instructions

Delete several documents, files, or folders in one call. confirmCount must equal the number of paths, else CONFIRMATION_MISMATCH. Every path is resolved before anything is deleted, so a missing one fails the call with NOT_FOUND and changes nothing. Deleting a folder removes everything inside it, so list the folder alone, not its contents too. Continues past a failed delete unless stopOnError, and returns status, completed, failed, and remaining. Confirm the list with the user first.

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": {
      "projectId": "<projectId>",
      "paths": "<paths>",
      "confirmCount": "<confirmCount>"
    },
    "name": "delete_entities"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathsYesProject paths to delete
projectIdYesOverleaf project ID
stopOnErrorNoStop at the first failure instead of continuing
confirmCountYesThe number of paths, repeated after confirming the list with the user

Output Schema

NameRequiredDescriptionDefault
failedYes
statusYes
completedYes
remainingYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.0

TDQS

A4.4/5.0
Behavior5/5

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

Beyond destructiveHint=true and idempotentHint=false, the description discloses that every path is validated before anything is deleted (a missing path fails atomically with NOT_FOUND), that confirmCount mismatch raises CONFIRMATION_MISMATCH, that deletion continues past failures unless stopOnError, and what is returned. This is unusually rich behavioral disclosure for a destructive mutation.

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?

Five tight sentences, front-loaded with the operation, followed by constraints, failure semantics, and the user-confirmation requirement in decreasing order of importance. No filler or restatement of the title.

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?

For a destructive, multi-parameter batch tool this covers preconditions, atomicity, error codes, partial-failure behavior, and the confirmation ritual. Return fields are mentioned even though an output schema exists, so nothing an agent needs before calling is missing.

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; the description adds value by tying confirmCount to a specific failure mode (CONFIRMATION_MISMATCH) and warning that paths should not include folder contents because folder deletion is recursive. That goes meaningfully beyond the schema's own parameter text.

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?

The description opens with a specific verb and resource set: 'Delete several documents, files, or folders in one call,' making the batch scope explicit. It does not name a sibling tool (e.g., manage_entity) to contrast single-item operations against, so it stops short of full sibling differentiation.

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?

It gives clear operational guidance: confirm the list with the user first, and list a folder alone rather than its contents, which is genuinely actionable when-to-use advice. It does not name an alternative tool or state when not to use this one at all.

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