Skip to main content
Glama
Mipiti MCP Server
by Mipiti

Get Review Playbook

get_review_playbook

Fetch a threat model's review playbook to get the work procedure, open queue items, decision authority, paid acts, report shape, and active review run for guiding and recording review work.

Instructions

How to work this model's review queue, in one read: start here. Read it before deciding anything on the model, and again after a round of work. Read-only on the model; it opens a review run for you (or reuses your open one), which every later write to the model is recorded under.

It returns:

  • procedure: the order of work, the rules, how each kind of review-queue item is worked (what to verify, where, and which tool acts on each outcome) and the report's shape. Follow it.

  • open: the model's open items by kind, in the queue's order, with their ids, decision counts, tools, and whether only a person acts on them.

  • authority: for each decision, the tiers you may decide at with evidence and without, and a status: delegated, parked (the call parks it for a person), outside (it proceeds, recorded outside policy), person_only or person.

  • paid: the paid acts the open items lead to and the tool that estimates each. Run one only with the person's agreement to its estimate, or within the workspace's spending allowance.

  • report: what to report when you are done.

  • review_run: the run you are working under. Close it with close_review_run and give the person its digest.

Pass evidence on every judgment. A refused judgment is parked for a person: never retry it.

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": {
      "server_version": "<server_version>",
      "model_id": "<model_id>"
    },
    "name": "get_review_playbook"
  }
}

Input Schema

NameRequiredDescriptionDefault
model_idYesID of the threat model.
server_versionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.106.1

TDQS

A3.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so well: it discloses that the tool is read-only on the model yet creates or reuses an open review run that records every later write. It also states the failure semantics — 'A refused judgment is parked for a person: never retry it' — and constrains paid acts to a person's estimate or the workspace allowance, which are non-obvious operational facts.

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?

The imperative opener is front-loaded and the bullets are organized by returned field with semantics rather than types. It is longer than most descriptions, and since an output schema exists, some of the return-value enumeration overlaps structured data, but each bullet still carries behavioral meaning.

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 read-only entry-point tool with an output schema, the description covers purpose, timing, side effects, decision authority, paid-act guardrail, failure handling, and the closing handoff. Completeness is only dented by leaving server_version unexplained and by the unqualified 'evidence' instruction that maps to no parameter here.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description never mentions model_id or server_version; schema coverage is only 50% (server_version is undocumented anywhere), so the description is the only place that gap could be closed and it isn't. The only parameter-adjacent instruction, 'Pass evidence on every judgment', refers to a field not in this tool's schema, which adds confusion rather than meaning.

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: it returns the procedure for working a model's review queue, plus the open items, decision authority tiers, paid acts and report shape. That is far more concrete than the title, and the phrase 'start here' plus the pointer to close_review_run separates it from get_review_queue and get_review_run. It never explicitly contrasts itself with those siblings, which keeps it below a 5.

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?

'Read it before deciding anything on the model, and again after a round of work' is an explicit when-to-use rule with a clear entry point. Follow-up behavior is also prescribed: close the run with close_review_run and hand the person the digest. No when-not-to-use or exclusion against get_review_queue/get_review_run is stated.

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

Deploy Server

Other Tools