Skip to main content
Glama

delete

Destructive

Delete exact facts or dynamic pages from personal memory after explicit user authorization, reusing remaining snapshots without re-verification.

Instructions

Delete exact Facts with an optional page description, or delete dynamic pages, only after explicit current-turn user authorization. On applied, reuse surviving Page Snapshots and receipts; do not verify with read or list.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
operationsYesAuthorized exact deletions; each path must be unique.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.2
    • addedInput schema / $defs / DeleteFactOperation / properties / description
      Added value: +{
      +  "anyOf": [
      +    {
      +      "maxLength": 80,
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "Replacement page description to apply with the Fact deletion.",
      +  "title": "Description"
      +}
  2. Changed4 schema fields changedv0.7.0
    • changedInput schema / $defs / DeleteFactOperation / properties / fact / $ref
      Previous value: -"#/$defs/Fact"New value: +"#/$defs/FactSelector"
    • removedInput schema / $defs / Fact
      Removed value: -{
      -  "additionalProperties": false,
      -  "properties": {
      -    "basis": {
      -      "description": "Evidence basis: stated for the user's explicit statement; observed only where the Agent Contract permits a repeated behavioral observation.",
      -      "enum": [
      -        "stated",
      -        "observed"
      -      ],
      -      "title": "Basis",
      -      "type": "string"
      -    },
      -    "content": {
      -      "description": "One complete, independently maintainable, single-line assertion.",
      -      "maxLength": 4096,
      -      "title": "Content",
      -      "type": "string"
      -    }
      -  },
      -  "required": [
      -    "basis",
      -    "content"
      -  ],
      -  "title": "Fact",
      -  "type": "object"
      -}
    • addedInput schema / $defs / FactSelector
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "basis": {
      +      "description": "Evidence basis: stated for the user's explicit statement; observed for Agent derivation or inference from current visible material.",
      +      "enum": [
      +        "stated",
      +        "observed"
      +      ],
      +      "title": "Basis",
      +      "type": "string"
      +    },
      +    "content": {
      +      "description": "Exact basis and content copied from an existing Page Snapshot.",
      +      "maxLength": 4096,
      +      "title": "Content",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "basis",
      +    "content"
      +  ],
      +  "title": "FactSelector",
      +  "type": "object"
      +}
    • changedInput schema / properties / operations / maxItems
      Previous value: -20New value: +15
  3. First observedv0.1.0

TDQS

A4.7/5.0
Behavior5/5

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

Annotations already mark the tool as destructive, but the description adds substantial behavioral context: the authorization prerequisite, the two distinct delete targets, and the unusual post-apply instruction to reuse surviving Page Snapshots and receipts rather than re-verifying. This goes well beyond the structured annotation hints.

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 two tight sentences with no filler. The core action and authorization gate are front-loaded, and the post-apply guidance about reuse and non-verification earns its place by conveying critical workflow details.

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 write operation with a detailed schema, annotations, and output schema, the description supplies the necessary prerequisites, acceptable targets, and post-apply behavior. Nothing essential for correct invocation is missing.

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%, with rich per-property explanations for path, if_version, target, authorization, and FactSelector. The description adds only high-level context such as optional page description and exact facts, which is useful but not necessary since the schema already documents all parameters thoroughly.

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 precise verb and resources: 'Delete exact Facts with an optional page description, or delete dynamic pages.' This clearly distinguishes the tool from siblings like read, list, move, and update, and leaves no doubt about what operation it performs.

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?

The description explicitly states the required condition: 'only after explicit current-turn user authorization.' It also gives direct behavioral guidance by saying 'do not verify with read or list,' which steers the agent away from sibling tools and clarifies the expected workflow after deletion.

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

Deploy Server

Other Tools