Skip to main content
Glama

postmortem

Capture testing findings, track fixes, and hold agent retrospective meetings that yield actionable, per-project artifacts read before the next plan.

Instructions

Postmortem mode: while testing sends fixers back, you keep a running draft of every finding; when all fixers are done the agents that did the work meet with you (hold_postmortem) and leave actionable artifacts, kept per project and read back before the next plan. Off by default: action enable turns it on for a project ONLY when the human asked for postmortem meetings, retrospectives, or agents improving themselves or each other; reason quotes their words verbatim (recorded in the project's log and the audit log). Nothing infers it. A heads-down run inherits it from its contract (propose_contract sets it); the runner then records a finding by itself when a submission is sent back after testing. disable turns it off and keeps stored postmortems. record adds a finding to the draft of a scope (execution_id for a run, or work for at-the-table work): {summary, detected_by, responsible[] (persona names, or "orchestrator"), category, task?, evidence[] (refs only: sha256: blob refs, event ids, commit shas, paths)}. fix sets a finding's fix {status: pending|fixed|abandoned, by?, ref?}; in a run, retries, merges and failures update fixes by themselves. draft returns the findings, what is still pending and whether the meeting can be held. lessons returns the active lessons of a project (always, whether or not the mode is on); list shows its drafts and postmortems; read returns a postmortem's full record (every turn) for you to show the human verbatim.

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": {
      "action": "<action>"
    },
    "name": "postmortem"
  }
}

Input Schema

NameRequiredDescriptionDefault
pmNoread: the postmortem (pm-…) hold_postmortem returned.
fixNofix: the finding's fix.
workNoA short label for at-the-table work (for example "checkout redesign") when there is no run. Give this or execution_id.
actionYesenable, disable, record, fix, draft, lessons, list or read.
reasonNoenable / disable: the human's own words asking for it (or for turning it off), quoted verbatim. Never invent it.
findingNorecord: the finding.
projectNoThe project: a directory inside its git repository (resolved with git rev-parse --show-toplevel; refused outside a git work tree or with submodules), or a project key returned earlier.
finding_idNofix: the finding (pmf-…).
execution_idNoThe heads-down run (exe-…) the draft belongs to. Give this or work.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations, the description discloses the off-by-default state, audit logging of reasons, automatic runner recording on sent-back submissions, automatic fix updates from retries/merges/failures, and the fact that disable preserves stored postmortems. These are meaningful behavioral details for a stateful multi-action tool.

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

Conciseness3/5

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

The description is front-loaded with the mode concept and uses no obvious filler, but it packs eight actions into one dense paragraph. An action-by-action structure would make it easier to scan without losing the useful behavioral details.

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 high-complexity, nine-parameter tool with no output schema, it covers defaults, enablement rules, inheritance, automatic behavior, storage, and the practical results of draft, lessons, list, and read. It is largely complete, though the return shapes for some read actions are described only briefly.

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%, so the schema already explains most parameters, including finding fields, evidence refs, and the work/execution_id distinction. The description restates some of those semantics but adds limited parameter meaning beyond the schema.

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 clearly frames this as postmortem-mode management and distinguishes the meeting step from hold_postmortem. It covers all eight actions specifically, though the multi-action scope means it does not reduce to a single verb+resource as cleanly as a focused tool.

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?

It gives explicit when-to-use rules: enable only when the human asked for postmortems/retrospectives, nothing should infer it, runs inherit it from contracts, and disable keeps stored postmortems. It also explains what each read-oriented action is for, including draft, lessons, list, and read.

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