past.dev

Delete data points from a project's memory

delete_memory

DestructiveIdempotent

Deletes data points from a project's memory by their source ids, as POST /api/v1/data-points/delete does: each data point and every memory past drew from it leave recall at once, and their stored copies and index entries are purged in the background. A recall names each source's id as sourceId. Every id must name a live data point of the project, or nothing is deleted and the refusal names the ids that do not. Destructive: call it without confirm first, put the sentence it answers to the person, and call again with confirm: true only if they agree. It answers the deletion's operationId; get_memory_deletion says when the purge is done. Deleting spends no credits. Needs project Write.

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": {
      "sourceIds": "<sourceIds>",
      "confirm": "<confirm>"
    },
    "name": "delete_memory"
  }
}

Input Schema

Name	Required	Description
`confirm`	Yes	true only once the person has agreed to the sentence an unconfirmed call answered with.
`project`	No	The project's slug, exactly as list_projects returned it. Omit it only when the organization has one live project.
`sourceIds`	Yes	The source ids to delete, 1 to 1,000, exactly as recall_memory or ingest_memory returned them.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 23, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds substantial operational context: deletion is atomic across all sourceIds, removal from recall is immediate while stored copies and index entries are purged in the background, and deleting spends no credits. These details go well beyond the annotations.

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?

The description is front-loaded with purpose, then moves through atomicity, confirmation workflow, return value, follow-up tool, and constraints. Despite covering a destructive multi-step operation, every sentence carries relevant operational information.

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?

Although there is no output schema, the description explains that the response contains the deletion's operationId and that get_memory_deletion reports when the purge finishes. Combined with the destructive annotations and full schema coverage, it provides everything needed to call the tool correctly.

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 schema already documents all parameters. The description still adds useful meaning: source ids must name live data points of the project and must come from recall_memory or ingest_memory, and it contextualizes the confirm workflow beyond the schema's boolean description.

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 states a specific verb and resource: deletes data points from a project's memory by source ids. It also distinguishes the tool from related siblings by noting that it returns an operationId and that get_memory_deletion is the follow-up for purge completion.

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 gives an explicit two-step confirmation workflow: call without confirm first, present the resulting sentence to the person, and call again with confirm: true only if they agree. It also names the follow-up tool for checking purge completion and states the required permission (project Write).

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

All past.dev tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?