Skip to main content
Glama

wrap_auto

Persist a session wrap without interactive review when context is about to be lost, applying low-risk updates immediately and staging high-risk changes for user confirmation.

Instructions

Tier 2 of auto-wrap: persist a session wrap WITHOUT interactive review, when context is about to be lost (compaction, session end) or the user declined to review. Use the normal interactive /wrap when the user is present and reviewing — only reach for this as a safety net. The agent supplies the synthesized wrap; this tool applies LOW-RISK fields (next_move, open_questions, evidence_of_progress) immediately and STAGES high-risk changes (status, mode, blocked, decisions) as an unconfirmed record for /start to surface and the user to confirm. Always logs a session_wrapped marker. Never put a status change or a decision in pending_review expecting it to take effect now — staged items are proposals, not writes.

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": {
      "entity_id": "<entity_id>",
      "summary": "<summary>"
    },
    "name": "wrap_auto"
  }
}

Input Schema

NameRequiredDescriptionDefault
summaryYesOne-line synthesized summary of what happened this session.
triggerNoWhat triggered it: precompact | sessionend | manual-no-review.
entity_idYesEntity being wrapped.
next_moveNoLOW-RISK, applied now — the concrete next action.
session_idNoHost session id, when known.
open_questionsNoLOW-RISK, merged now — unresolved threads.
pending_reviewNoHIGH-RISK — staged for review, NOT applied. Surfaced at next /start for confirm/edit/discard.
evidence_of_progressNoLOW-RISK, appended now — what actually shipped or moved.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.11.0
    • removedInput schema / properties / pending_review / properties / blocked / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / pending_review / properties / blocked / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  2. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only supply readOnlyHint=false, so the description carries the real burden and does: it splits behavior into fields applied immediately vs staged as an unconfirmed record, explains where staged items surface (/start), states that a session_wrapped marker is always logged, and warns that staged status/decisions are proposals, not writes. That is exactly the non-obvious contract an agent needs before invoking.

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 purpose and the safety-net framing are front-loaded, then the applied-vs-staged split, then the failure-mode warning. Every sentence carries distinct information; the final sentence is a genuine misuse guard rather than padding.

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 an 8-parameter tool with a nested pending_review object and no output schema, the description covers the write contract well. The only gap is that, with no output schema, it does not say what the call returns (e.g., what the recorded marker or staged-record handle looks like), which an agent might want to report back.

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 per-parameter meaning is already documented; the description nonetheless adds the cross-cutting semantic that next_move/open_questions/evidence_of_progress are LOW-RISK and applied now while pending_review contents are HIGH-RISK and staged. It does not separately explain trigger values or session_id, but the schema covers those.

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?

States a specific verb and resource ('persist a session wrap') plus a defining scope qualifier ('WITHOUT interactive review') and frames itself as Tier 2 of a two-tier scheme. An agent can distinguish it from the interactive /wrap and from siblings like entity_update or memory_commit without opening any schema.

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?

Gives explicit triggers (compaction, session end, user declined to review) and names the alternative ('the normal interactive /wrap when the user is present and reviewing'), plus frames itself as a safety net. This is a when/when-not/alternative triad, not implied usage.

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