Skip to main content
Glama

Send a follow-up prompt to a finished swarm task

swarm_followup
Destructive

Continue a completed cb_* or sess_* task in its original conversation session by sending a follow-up prompt, so you can build on prior context without starting over.

Instructions

Continue a finished, non-ephemeral cb_* or sess_* task in the same conversation session.

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": {
      "taskId": "<taskId>",
      "prompt": "<prompt>"
    },
    "name": "swarm_followup"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo
promptYes
taskIdYes
fallbackModelNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the description only needs to add context. It does add that the prompt joins the existing conversation session and requires a finished task, but says nothing about what 'destructive' means here, whether quota is consumed, or whether the prior task output is preserved or replaced.

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?

A single front-loaded sentence with no redundant wording and the constraints immediately visible. Its brevity is efficient, though it leaves no room for the missing model/fallbackModel guidance.

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

Completeness2/5

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

For a destructive, non-idempotent session mutation with four undocumented parameters and no output schema, the description is thin. It omits model/fallbackModel semantics, the qd_* task type, and any statement of what the call returns, so an agent cannot invoke it fully confidently.

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 description coverage is 0%, so the description should carry the parameter burden. It partially documents taskId (limiting it to cb_* and sess_*) but omits the qd_* prefix that the schema pattern explicitly permits, and says nothing about when to supply model versus fallbackModel.

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?

The description uses a clear verb ('Continue') on a specific resource ('finished, non-ephemeral cb_* or sess_* task') and adds the key scope detail 'same conversation session'. It does not distinguish itself from the sibling zcode_followup, leaving the agent to guess which follow-up tool applies to which backend.

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?

The preconditions ('finished', 'non-ephemeral') are implied usage guidance, telling the agent when the tool is valid. There is no explicit when-not guidance and no named alternative such as zcode_followup, so the agent must infer the routing itself.

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