Skip to main content
Glama

request_deletions

Ask your owner to approve several deletions at once: up to 50 items, each a file (kind "file", container, target = file id or path), a folder (kind "folder", container, target = folder path), an empty container (kind "container", container…

Instructions

Ask your owner to approve several deletions at once: up to 50 items, each a file (kind "file", container, target = file id or path), a folder (kind "folder", container, target = folder path), an empty container (kind "container", container = its id or name), a memory space (kind "memory_space", container = the space's id or name) or a memory fact (kind "fact", target = the fact id), with a short reason the owner reads. Every item is checked now; if any can't be deleted nothing is asked, and the error names each bad item. Nothing is deleted yet: the owner approves all, some or none on the Approvals page, and Connapse then deletes the approved items itself, skipping any that are gone or changed since you asked. Call deletion_status with the returned id (and waitSeconds) to read each item's outcome; don't delete the items yourself.

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": {
      "items": "<items>"
    },
    "name": "request_deletions"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYesThe deletions, in the order the owner should see them: a JSON array of {"kind", "container", "target", "reason"} objects

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.4.2

TDQS

A4.9/5.0
Behavior5/5

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

Annotations only declare destructiveHint=false, and the description corroborates that by explaining nothing is deleted at request time. It goes well beyond annotations by disclosing the all-or-nothing upfront validation ('if any can't be deleted nothing is asked, and the error names each bad item'), partial approval by the owner, post-approval deletion by Connapse, stale-item skipping, and the polling mechanism.

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?

Purpose and cap are front-loaded and almost every clause carries operational information, including the error and polling behavior. It is a single dense paragraph with mild redundancy ('with a short reason the owner reads' partly restates the reason field), and could be easier to scan if the per-kind rules were list-formatted.

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?

There is no output schema, yet the description explains what comes back (an id to pass to deletion_status, plus waitSeconds) and how per-item outcomes are read. For a single-parameter, batch-approval tool, the validation, approval, and follow-up lifecycle is fully covered.

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

Parameters5/5

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

Schema coverage is 100% for the single 'items' parameter, so the baseline would be 3, but the description adds substantial meaning: the 50-item cap, per-kind semantics for container vs target (e.g. kind 'file' uses target = file id or path; kind 'container' uses container = its id or name), the purpose of 'reason' as owner-facing text, and ordering significance.

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?

The description opens with a specific verb and resource: 'Ask your owner to approve several deletions at once', and immediately bounds the scope ('up to 50 items'). It enumerates the five item kinds (file, folder, container, memory_space, fact) and their key fields, so an agent can distinguish this approval-request flow from the direct-delete siblings like delete_file or container_delete.

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?

It states explicitly when to use this tool (batch deletions needing owner approval), what to do next ('Call deletion_status with the returned id (and waitSeconds)'), and what not to do ('don't delete the items yourself'). The alternative path for reading outcomes is named outright, leaving little to inference.

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