Skip to main content
Glama
Mipiti MCP Server
by Mipiti

Close Review Run

close_review_run

Close a threat-model review run with your notes and get a platform-generated digest of its decisions, evidence, parked items, spend, and undo actions.

Instructions

Close your review run on the model with your notes, and get its digest to give the person: what the run decided and on what evidence, what it parked for them, what it spent, your notes beside them, and the act that undoes each decision. The digest is read from the platform's records, not from your notes. Mutating: records the run's end.

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": "close_review_run"
  }
}

Input Schema

NameRequiredDescriptionDefault
notesNoWhat you did and why, in your words (shown as yours).
run_idNoThe run to close. Empty (default): your open run.
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

B3.4/5.0
Behavior3/5

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

With no annotations present, the description carries the full burden; it does disclose that the call is mutating ('records the run's end') and that the digest is read from platform records rather than from your notes. It does not say whether closing is reversible, what happens to parked items afterwards, or what permissions are required.

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 verb and resource are front-loaded in the first clause, and the digest contents are enumerated in one compact list. The middle sentence enumerating digest parts is slightly long but not wasteful.

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?

An output schema exists, so the digest's return shape needn't be spelled out, yet the description spends most of its length on it while omitting the mutation consequences an agent needs for a non-read-only tool with no annotations.

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 75% and the schema already explains notes and run_id (including the empty-default meaning 'your open run'). The description adds only the notion that notes appear 'beside' the digest and are attributed to you, leaving model_id and server_version unexplained 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?

States a specific verb and resource ('Close your review run on the model') plus the secondary effect of returning a digest. It is clearly distinct from the read-only sibling get_review_run, though it never names that sibling explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied: you close the run with your notes and hand the digest to 'the person'. There is no explicit when-to-use/when-not-to-use guidance and no named alternative for merely inspecting a run without closing it.

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