Skip to main content
Glama

ctxstore — memory that follows you across models

Delete Fact

delete_fact
DestructiveIdempotent

Soft-delete a stored fact by its UUID (Smart Forget). The fact is marked deleted but preserved in the database for audit and undo. Excluded from all normal searches. Use when information is no longer accurate or relevant.

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": {
      "fact_id": "<fact_id>"
    },
    "name": "delete_fact"
  }
}

Input Schema

NameRequiredDescriptionDefault
fact_idYesThe UUID of the fact to delete

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description needed to add something beyond the safety flags — and it does: the deletion is soft, the record is preserved for audit and undo, and it is excluded from all normal searches. That tells the agent exactly what is and is not lost, which is the key behavioral question for 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?

Four short sentences, front-loaded with the action and its reversibility, then the visibility consequence, then the usage trigger. Every sentence adds distinct information and nothing is repeated from the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter mutation tool with no output schema, the definition covers what happens, whether it is recoverable, and how it affects search results. The only minor gap is error or precondition behavior (e.g., an unknown UUID), which is not essential to calling it correctly.

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 coverage is 100% with a single documented parameter ('The UUID of the fact to delete'), and the description only restates 'by its UUID'. With the schema already doing the work, the baseline of 3 applies; no extra format or sourcing guidance for the UUID is added.

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 states a specific verb and resource ('Soft-delete a stored fact by its UUID') and pins down the deletion semantics with the 'Smart Forget' alias, so an agent immediately knows this is a reversible removal, not a hard delete. It does not explicitly contrast with siblings such as move_fact or reinforce_fact, but the soft-delete framing is distinctive enough to disambiguate the operation.

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?

'Use when information is no longer accurate or relevant' gives a concrete trigger condition, which is more than most mutation tools offer. It stops short of naming when-not-to-use cases (e.g., prefer move_fact when the fact is merely misclassified) or pointing at an alternative sibling, so it is clear context without exclusions.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.