Skip to main content
Glama

Delete data store entries

delete_workspace_data
Destructive

Permanently deletes selected entries from a workspace key-value store by single key, named keys, or prefix, and previews the effect unless confirmation is set.

Instructions

Permanently deletes from the per-workspace key-value store. Pass exactly ONE of: key (one entry), keys (a NAMED list — up to 100 in a single call, and the right tool for cleaning up your own entries while leaving everything else alone), or prefix (EVERY entry under it, e.g. prefix:"chunk:" clears chunk:0…chunk:99 — for a dataset you own outright). Prefer keys over prefix whenever the store also holds entries you did not create: a prefix that looks like yours can match somebody else's. An empty prefix is refused. Requires confirm=true — call without confirm first to preview.

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": {
      "workspaceId": "<workspaceId>"
    },
    "name": "delete_workspace_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyNoDelete this one entry.
keysNoDelete exactly these entries and nothing else. Up to 100 per call.
prefixNoDelete every entry whose key starts with this.
confirmNoMust be true to delete. Omit/false returns a preview only.
workspaceIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.53.0

TDQS

A5/5.0
Behavior5/5

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

Annotations only declare destructiveHint=true; the description adds substantial behavior beyond that: deletion is permanent, an empty prefix is refused, the call without confirm returns a preview instead of deleting, and a single call caps `keys` at 100. These are exactly the operational traits an agent needs before invoking a destructive tool.

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?

Front-loaded with the effect and the selection rule, then the safety warning about shared stores, then the confirm requirement. Every sentence carries a distinct constraint; nothing is decorative or repeated from the schema.

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 five-parameter destructive tool with no output schema, the description covers the mutation semantics, the selector exclusivity, the limits, the refusal case, and the dry-run preview path. An agent has everything needed to call it correctly and safely.

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 high (80%) and already documents each parameter's basic meaning, but the description adds semantics the schema does not express: the one-of exclusivity between `key`, `keys`, and `prefix`, the concrete prefix example ('chunk:' clearing chunk:0…chunk:99), and the confirm-as-preview contract. That is real value beyond structured fields.

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 first sentence states a specific verb plus resource plus scope: 'Permanently deletes from the per-workspace key-value store.' That is enough to separate it from workspace-level or block-level deletion siblings without opening any 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?

It states the mutually exclusive selector modes up front ('Pass exactly ONE of'), then gives an explicit decision rule: prefer `keys` over `prefix` whenever the store holds entries you did not create, because a prefix can match somebody else's keys. It also names the conditions for each mode (one entry vs. your own bulk cleanup vs. a dataset you own outright), which is genuine when-to-use guidance rather than restated schema text.

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