Skip to main content
Glama

Steer a running Berrys agent plan

playground_run_steer

Add a note to a production plan that is running: it applies to steps that have not started and later outputs are reviewed against it. Steps already generating are unchanged. Ended runs cannot be steered; send playground_brief_start with the run’s conversationId instead. Requires agent:start.

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": {
      "projectId": "<projectId>",
      "runId": "<runId>",
      "message": "<message>"
    },
    "name": "playground_run_steer"
  }
}

Input Schema

NameRequiredDescriptionDefault
runIdYesRun ID returned by preparation or execution for this project.
messageYesUser’s creative brief or steering instructions for the current run.
projectIdYesID of the Playground project chosen for this task; obtain it from project creation, an explicit project link or current context.

Output Schema

NameRequiredDescriptionDefault
nextYesSuggested next action; it does not authorize spending.
runIdYes
statusYes
conversationIdYes
retry_after_secondsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (which only say this is a non-read-only, non-idempotent, non-destructive write), the description discloses the actual effect model: the note binds only to unstarted steps, steps already generating are unaffected, later outputs are reviewed against it, and ended runs are rejected. It also states the required agent:start permission, which no structured field conveys.

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?

Four short sentences, front-loaded with the action and its scope, then the exclusion and redirect, then the permission prerequisite. No restatement of the name or title and no filler.

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 three-parameter mutation with full schema coverage, annotations, and an output schema, the description supplies everything left uncovered: effect scope, non-retroactivity, the terminal-state failure mode and its alternative, and the auth requirement.

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 description coverage is 100%, so runId, projectId, and message are already documented. The description adds conceptual meaning to the message parameter (a note that binds future steps) but no format, length, or syntax detail beyond the schema; baseline 3 applies.

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?

Names a specific verb and resource — adding a steering note to a production plan that is currently running — and immediately scopes it to steps that have not started. It also contrasts itself with playground_brief_start for ended runs, so an agent can distinguish it from the sibling without opening either 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 explicit when-to-use conditions (plan is running, affected steps not yet started) and an explicit when-not plus alternative: ended runs cannot be steered, use playground_brief_start with the run's conversationId instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.