Skip to main content
Glama

run_routine

DestructiveIdempotent

Start an existing OpenBot routine by agent and routine ID, optionally appending payload data to its instruction; use list_agents to find routine IDs.

Instructions

Start an existing routine now. The optional payload is appended to the routine's instruction as data. A run has no retry key. Routine IDs come from list_agents.

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": {
      "agent": "<agent>",
      "routineId": "<routineId>"
    },
    "name": "run_routine"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYesAgent ID or exact name from list_agents
payloadNo
routineIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.4/5.0
Behavior3/5

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

Beyond the annotations, the description adds two genuinely useful behavioral facts: the payload is injected into the routine's instruction strictly as data, and there is no retry key, so repeated calls are not deduplicated by the caller. It does not explain what destructiveHint=true actually destroys or what openWorldHint=true means for side effects, which leaves an agent without the blast-radius information it needs for a destructive, open-world operation.

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?

Three short sentences, front-loaded with the action before the caveats, with no filler. The retry-key sentence is compact to the point of being cryptic on first read, but it earns its place as a safety warning.

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?

For a destructive, open-world mutation with no output schema and partially documented parameters, the description covers the core action, payload injection semantics, ID provenance, and retry caveat. It is still missing the consequences of a run (what destructive effects to expect) and the agent/routineId scoping relationship, both of which an agent would want before invoking it.

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 only 33% (only 'agent' is documented in the schema), so the description has to carry weight, and it does: it explains that payload is appended to the instruction as data and that routineId values come from list_agents. It does not clarify the relationship between agent and routineId (is the routine resolved within that agent's scope?), nor any format or length expectations for the two undocumented parameters.

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?

"Start an existing routine now" gives a specific verb (start), a specific resource (an existing routine), and a timing constraint (immediately rather than scheduling). It also points to list_agents as the source of valid IDs, which separates it from the listing/status siblings. It stops short of explicitly contrasting with any other execution-related tool, so it lands just below top marks.

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 rather than argued: the agent learns that this is the immediate-run path and that routine IDs must be obtained from list_agents first, which is a real prerequisite. There is no when-not guidance (e.g., when to schedule instead of run now) and no statement about what conditions must hold before a routine can be started.

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