Skip to main content
Glama
Mipiti MCP Server
by Mipiti

Revoke Co Disposition

revoke_co_disposition

Revoke a signed control-objective judgment—not-applicable disposition or risk acceptance—while keeping it in the audit trail; create a new judgment if the claim holds again.

Instructions

Revoke a signed judgment on a control objective: a not-applicable disposition or a risk acceptance. Mutating, and terminal: a revoked judgment is kept in the audit trail (list_co_dispositions) and never comes back; sign a new one if the claim holds again.

The objective returns to whatever posture its controls give it, gap included, and a revoked not-applicable disposition puts its objective back in what a build authors. So revoking one is refused (generation_active) while a control build holds the model. A judgment inherited from an ancestor model is revoked there, not here.

Use it when the person who owns a judgment withdraws it, or when it was recorded in their name before they made the call.

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>",
      "disposition_id": "<disposition_id>"
    },
    "name": "revoke_co_disposition"
  }
}

Input Schema

NameRequiredDescriptionDefault
evidenceNo
model_idYesID of the threat model the judgment is recorded on.
disposition_idYesThe judgment's ``id`` (from ``create_co_disposition``, ``create_risk_acceptance`` or ``list_co_dispositions``).
server_versionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.106.1
    • addedInput schema / properties / evidence
      Added value: +{
      +  "default": "",
      +  "type": "string"
      +}
  2. Addedv0.104.0

TDQS

A4.4/5.0
Behavior5/5

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

No annotations are supplied, so the description carries the full burden and does so: it declares the tool mutating and terminal, that the record is retained in the audit trail via `list_co_dispositions` and never resurrected, and that the objective reverts to its controls-derived posture including gap status. It also discloses the specific refusal error (`generation_active`) and the ancestor-model delegation rule.

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?

Front-loaded with verb, resource, and object scope, then behavior, then usage — a logical order with no filler. However, 'a revoked not-applicable disposition puts its objective back in what a build authors' is grammatically tangled, and the following 'So revoking one is refused...' forces the reader to reconstruct the causal link.

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

Completeness5/5

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

For a destructive, terminal mutation with an output schema already covering return values, the description supplies everything material: irreversibility, audit retention, resulting state of the objective, the blocking error condition, and the ancestor-model case. The only residual gap is the undocumented `evidence` parameter, which is minor against the behavioral coverage.

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?

Schema coverage is only 50%, and the description adds nothing about parameters — `evidence` (which presumably records why the judgment is being withdrawn) and `server_version` are undocumented in both the schema and the description. Only `model_id` and `disposition_id` are explained, and that explanation comes from the schema, not the description.

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 ('Revoke a signed judgment on a control objective') and immediately narrows the object to the two judgment kinds it covers: a not-applicable disposition or a risk acceptance. It implicitly contrasts with the sibling `list_co_dispositions` (audit trail retains the record) and `create_co_disposition`/`create_risk_acceptance` ('sign a new one'), so an agent can locate it in the tool family without opening a 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 an explicit when-to-use condition ('when the person who owns a judgment withdraws it, or when it was recorded in their name before they made the call') and explicit exclusions ('A judgment inherited from an ancestor model is revoked there, not here'). It also names the precondition that blocks invocation ('refused (`generation_active`) while a control build holds the model'), which is exactly the guidance an agent needs before calling.

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