Skip to main content
Glama
Mipiti

Mipiti MCP Server

by Mipiti
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Strengthen Controls

strengthen_controls

Strengthens a threat model's controls by addressing objectives whose mitigation groups leave them uncovered. Estimates credit cost, then starts a background run upon confirmation.

Instructions

Strengthen a model's controls: work on the objectives whose mitigation groups the background judge found do not cover them (the uncovered and undecided of get_control_generation_status's diagnosis). Mutating only with confirm_estimate=True; consumes credits then. not_judged objectives have nothing to strengthen from: judge them first with judge_objectives.

  1. Call with confirm_estimate=False (the default): nothing starts or is charged; the answer carries diagnosis, scope, estimate (credits, per_objective, basis) and the model_version / set_revision the model stands at. Show the user the estimate.

  2. Once they agree, call with confirm_estimate=True and those two values (their review of the model as it stood). A background run starts (started: true); poll get_control_generation_status. It holds the model like any build: pausable, resumable, discardable.

A gap only the environment can close (hosting, a third party) is never answered with a control: an accepted assumption stating it is bound into the group; otherwise an assumption proposal waits in the review queue (get_review_queue / decide_proposal) and the objective counts as awaiting_assumption. A rejected one is not proposed again.

Refusals come back as data, {started: false, http_status, code}: 409 review_stale (the model or its controls changed since the estimate: confirm again with the values returned), 409 generation_active (a build holds the model), 402 (the balance cannot cover the estimate).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
co_idsNoOptional comma-separated objective IDs, of those diagnosed uncovered or undecided; omit for all.
model_idYesID of the threat model.
set_revisionNoWith ``confirm_estimate=True``: the estimate's value.
model_versionNoWith ``confirm_estimate=True``: the estimate's value.
server_versionYes
confirm_estimateNoFalse (default) estimates; True starts the run.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.84.0
    • changedInput schema / properties / co_ids / description
      Previous value: -"Optional comma-separated objective IDs to restrict the run\nto, of those the diagnosis lists as uncovered or undecided. Omit\nfor all of them."New value: +"Optional comma-separated objective IDs, of those diagnosed\nuncovered or undecided; omit for all."
    • changedInput schema / properties / confirm_estimate / description
      Previous value: -"False (default) returns the estimate and starts\nnothing; True starts the run."New value: +"False (default) estimates; True starts the run."
    • addedInput schema / properties / model_version
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "With ``confirm_estimate=True``: the estimate's value."
+}
    • addedInput schema / properties / set_revision
      Added value: +{
+  "anyOf": [
+    {
+      "type": "integer"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "With ``confirm_estimate=True``: the estimate's value."
+}
  2. Addedv0.83.1

TDQS

A4.9/5.0
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 thoroughly: it discloses that credits are only consumed with confirm_estimate=True, that the answer carries diagnosis/scope/estimate/model_version/set_revision, that runs are pausable/resumable/discardable, and it enumerates refusal outcomes as data with specific status codes (409 review_stale, 409 generation_active, 402).

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?

Long but justified by tool complexity, and strongly front-loaded: the purpose is in the first clause before the numbered workflow. The two-step procedure is enumerated, and the refusal section is compact and scannable. No filler sentences.

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 multi-step, credit-consuming mutation with rich refusal semantics, the description covers the estimate/confirm cycle, preconditions, side effects, and error handling. Output schema exists, yet the description still usefully summarizes answer fields, leaving nothing an agent needs missing.

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 83%, so the schema already documents most parameters. The description still adds meaning: co_ids is constrained to objectives diagnosed uncovered/undecided, and model_version/set_revision are tied to the estimate values that must be echoed back on confirmation. It does not add syntax beyond that, so not a 5.

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+resource ('strengthen a model's controls') and precisely scopes the work to objectives whose mitigation groups the judge found uncovered/undecided. It distinguishes itself from sibling tools by naming get_control_generation_status, judge_objectives, and get_review_queue in their roles.

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?

Explicit two-step workflow: call with confirm_estimate=False to estimate, then True to start. It names the preconditions (not_judged objectives need judge_objectives first) and the polling/alternative path (get_control_generation_status, review queue). When and when-not is fully covered.

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