Skip to main content
Glama

archive_change

Destructive

Previews and applies an explicit archive closeout after resolving overlaps and dependencies and verifying implementation with saved evidence; reports actual mutations and recovery.

Instructions

Explicit closeout: preview simulates official sync+archive in a temporary repo; inspect/read exposes every original input and exact spec diff. Resolve overlaps/dependencies, verify implementation using saved evidence, then explicitly apply the token with review confirmations. Concurrent edits invalidate previews. result reports actual mutations and recovery. Never archives from validation or task completion alone.

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": {
      "workspacePath": "<workspacePath>",
      "action": "<action>"
    },
    "name": "archive_change"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNo
pathNo
limitNo
tokenNo
actionYes
cursorNo
offsetNo
sectionNo
versionNo
dependsOnNo
overlapOrderNo
verificationNo
workspacePathYes
expectedRevisionNo
specDiffsReviewedNo
dependenciesReviewedNo
unknownTasksAcknowledgedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.1

TDQS

A4/5.0
Behavior5/5

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

Annotations only state destructive/not-read-only; the description goes far beyond them by disclosing that preview operates in a temporary repo, that concurrent edits invalidate previews, that apply requires a token plus three explicit review confirmations, and that the result action reports actual mutations and recovery paths. That is exactly the operational context an agent needs before invoking a destructive multi-phase tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Roughly 60 words for a five-mode destructive workflow is tight, and the safety-critical constraint ("Never archives from validation or task completion alone") is placed last where it is most salient. The semicolon-chained clauses are dense and occasionally hard to parse, but every clause carries distinct information.

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

Completeness3/5

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

The workflow, invalidation rule, and confirmation gates are covered, and the "result reports actual mutations and recovery" line partially compensates for the missing output schema. However, for a 17-parameter tool with zero schema descriptions, several call-construction details (revision pinning, pagination, section/version selection) are absent, so an agent could still mis-specify a call.

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?

With 17 parameters and 0% schema description coverage, the description carries the burden and only partly does so: it explains the action modes, the token for apply, the saved-evidence verification object, dependsOn/overlapOrder, and the review-confirmation booleans. It says nothing about expectedRevision, workspacePath, id/path, pagination (limit/cursor/offset), or the section/version selectors, leaving roughly half the surface undocumented.

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 names a specific operation ("Explicit closeout" / sync+archive) and enumerates the five modes of the tool: preview simulates the archive, inspect/read expose inputs and spec diffs, apply performs it, result reports mutations. That is well beyond a restatement of the name. It stops short of 5 because it never explicitly positions itself against the obvious siblings (validate_change, change_status), leaving the agent to infer the boundary.

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?

"Resolve overlaps/dependencies, verify implementation using saved evidence, then explicitly apply" gives an ordered precondition chain, and "Never archives from validation or task completion alone" is an explicit when-not rule that steers the agent away from archiving after mere validation. No named alternative tool or fallback is given, which keeps it from a 5.

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