Skip to main content
Glama

person_revision_restore

Destructive

Restore a person card to a revision from person_history. Snapshots the current card first, so the restore is non-destructive and archive state stays unchanged.

Instructions

Put a person card back to a revision from person_history (card and its synthesized_at). Snapshots the current card first, so it is never destructive. Archive state is unchanged.

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": {
      "slug": "<slug>",
      "revision_id": "<revision_id>"
    },
    "name": "person_revision_restore"
  }
}

Input Schema

NameRequiredDescriptionDefault
slugYesPerson slug: lowercase [a-z0-9-], e.g. "patrick-kells".
storeNoIn a household, which half the revision is from (person_history says): the shared directory entry, or this agent's relationship (the default). Ignored outside a household.
revision_idYesRevision id from person_history.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.16.1
    • addedInput schema / properties / store
      Added value: +{
      +  "description": "In a household, which half the revision is from (person_history says): the shared directory entry, or this agent's relationship (the default). Ignored outside a household.",
      +  "enum": [
      +    "directory",
      +    "relationship"
      +  ],
      +  "type": "string"
      +}
  2. Addedv0.5.1

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false and destructiveHint=true; the description goes further by disclosing the snapshot-before-write behavior and that archive state is untouched, which is exactly the context an agent needs before overwriting a card. The phrase "never destructive" sits in mild tension with destructiveHint=true (the current card state is indeed replaced, just recoverably), but the description does not misrepresent it as a read-only operation.

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?

Three short sentences, each doing distinct work: operation and source, safety behavior, and state side effect. The most decision-relevant facts lead.

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 mutation tool with annotations and no output schema, it covers the overwrite target, the automatic backup, and the archive-state invariant. It leaves open whether the restore creates a new history entry the agent could roll back to, and what the call returns, which slightly limits follow-up planning.

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%, so slug, revision_id, and the household-scoped `store` enum are already fully documented in the schema. The description adds only that the restored payload is the card and its synthesized_at; it says nothing about the `store` choice or revision id format. Baseline 3 applies when the schema carries the semantics.

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?

Names a specific verb and resource ("Put a person card back to a revision") and anchors the source of the revision in the sibling tool person_history. The closing clause "Archive state is unchanged" separates it from archive-state siblings such as person_archive/person_restore, so an agent can pick it without opening the schema.

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?

It implicitly states the precondition (a revision_id obtained from person_history) and clarifies the scope boundary against archive operations. There is no explicit "do not use this when..." for related tools like person_restore or memory_revision_restore, so it stops just short of full routing guidance.

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