MBEstudio

Re-prompt an agent

reprompt_agent

Idempotent

Ask the agent that owns a subsystem to try again, with your instruction. It sees the model, its last answer and the conflicts still open; its new answer is checked in context, retried on blocking conflicts, and replaces the open proposal for that subsystem. Nothing is committed. Needs model_id (a saved m_ model), subsystem and prompt. Paid. Call it directly: it charges what the job uses, never more than its estimated maximum or the max_spend_credits you set. request_id is optional; set one to make a retry safe. Returns job_id immediately. Poll get_job_status for later progress.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "reprompt_agent"
  }
}

Input Schema

Name	Required	Description	Default
`rows`	No	Only for cost_mode "agent_authored" on generate_safety_analysis: {conditions:[{target,description,severity,...}],modes:[{target,mode,severity,occurrence,detection,...}]}; with analysis "stpa": {losses:[{id,description}],hazards:[{id,description,losses}],controllers:[{target,processModel}],controlActions:[{from,to,name,ucas:[{id,type,context,contextVariables,hazards,constraint}\|{type,notApplicable,rationale}]}],feedback:[{from,to,name,updates}],constraints:[{id,name,text}]}.
`model`	No
`study`	No
`events`	No
`format`	No
`prompt`	No
`stop_s`	No
`analysis`	No	For generate_safety_analysis: fha, fmea, both (default) or stpa. stpa needs no standard.
`fidelity`	No
`model_id`	No	A model from a generation job (model_ id) or a saved studio model (m_ id); a saved model is read at the head of main.
`provider`	No
`standard`	No
`cost_mode`	No		managed
`max_depth`	No	Only for run_agent_swarm: levels of division, 1 to 3 (default 2). At 2 and 3, a subsystem the orchestrator judges too large for one agent is divided again inside its frozen boundary.
`subsystem`	No	For reprompt_agent: qualified name of the subsystem, e.g. "Rover::DriveUnit". For run_agent_swarm on a saved model: the subsystem to decompose one level further (its parts get the agents); leave it out to work on the whole system's subsystems.
`request_id`	No
`scenario_id`	No
`simulations`	No
`specification`	No	Only for cost_mode "agent_authored" on generate_system_model and build_full_system; see those tools for its schema.
`simulation_type`	No
`max_spend_credits`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 4, 2026

addedInput schema / properties / analysis / description

Added value: +"For generate_safety_analysis: fha, fmea, both (default) or stpa. stpa needs no standard."

changedInput schema / properties / analysis / enum

Previous value: -[
-  "fha",
-  "fmea",
-  "both"
-]New value: +[
+  "fha",
+  "fmea",
+  "both",
+  "stpa"
+]

changedInput schema / properties / rows / description

Previous value: -"Only for cost_mode \"agent_authored\" on generate_safety_analysis: {conditions:[{target,description,severity,...}],modes:[{target,mode,severity,occurrence,detection,...}]}."New value: +"Only for cost_mode \"agent_authored\" on generate_safety_analysis: {conditions:[{target,description,severity,...}],modes:[{target,mode,severity,occurrence,detection,...}]}; with analysis \"stpa\": {losses:[{id,description}],hazards:[{id,description,losses}],controllers:[{target,processModel}],controlActions:[{from,to,name,ucas:[{id,type,context,contextVariables,hazards,constraint}|{type,notApplicable,rationale}]}],feedback:[{from,to,name,updates}],constraints:[{id,name,text}]}."

First observedNov 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Beyond the annotations it discloses the mechanics: the agent sees the model, its last answer and open conflicts; the new answer is validated and retried on blocking conflicts; the previous open proposal is replaced; nothing is committed; it runs as a paid job that returns job_id immediately. One mild tension: idempotentHint=true while the description says to "set [request_id] to make a retry safe," which implies retries are unsafe without one — a hint inconsistency rather than an outright contradiction.

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 purpose and effect, then required parameters, then cost, then return/polling — a sensible order with no filler. A few clauses ("Call it directly", the charging sentence) are denser than they need to be, but nothing is redundant.

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 an asynchronous, paid, mutating job with no output schema, the description covers cost capping, idempotency, non-commitment, and the follow-up polling tool, which is what an agent needs to invoke it correctly. Missing only an explicit statement about what happens to parameters irrelevant to this operation.

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?

With only 29% schema description coverage across 21 shared parameters, the description compensates by naming the parameters that actually matter here (model_id as a saved m_ model, subsystem, prompt) and by adding semantics the schema lacks for request_id (idempotency) and max_spend_credits (hard spend ceiling, never above the estimate). It does not explicitly say the other 16 properties are irrelevant to this call, which would fully close the gap.

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?

"Ask the agent that owns a subsystem to try again, with your instruction" names a specific verb (re-prompt/re-run), a specific actor-scope (the agent owning a subsystem), and the distinguishing effect (replaces the open proposal for that subsystem). An agent can separate this from run_agent_swarm or mbe_commit without opening the schema.

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?

It states the precondition (a subsystem with an open proposal from an agent) and the follow-up step ("Poll get_job_status for later progress"), and rules out a commit interpretation with "Nothing is committed." It stops short of explicitly contrasting the case where you should call run_agent_swarm instead of re-prompting an existing agent, but the context is clear enough to act on.

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

All MBEstudio tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?