Skip to main content
Glama

Send a follow-up to a ZCode task

zcode_followup
Destructive

Continue a finished ZCode task by sending a follow-up message in the same conversation, preserving earlier context so the agent can build on prior work.

Instructions

Continue a FINISHED task with another message in the same ZCode conversation (it keeps its earlier context). Returns immediately; use zcode_wait afterwards. The task must not be running, and must still be visible in ZCode's sidebar (not archived).

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": "zcode_followup"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYes
taskIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.0

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations (destructiveHint=true, idempotentHint=false, openWorldHint=true), the description adds genuinely useful behavior: the call is non-blocking ("Returns immediately"), it appends into the same conversation retaining prior context, and it requires a terminal, non-archived task state. What it omits is the mutation's consequence detail — whether earlier task output is altered and what an invalid/rejected call looks like.

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?

Two dense sentences with no filler: the core action and context-retention note come first, then the async caveat and next-step tool, then the state preconditions. Every clause carries operational information.

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 2-parameter mutation with no output schema, the definition covers the invocation conditions well but not the return path — it says the call returns immediately without stating what it returns (e.g., a handle or task id) or how zcode_wait then locates the task. That missing return-shape context is the main gap for a tool whose whole purpose is to chain into zcode_wait.

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 0%, so the description must carry parameter meaning and only partially does: "another message" maps to prompt and "task" maps to taskId. It never mentions the required taskId format (the sess(ion)_[\w-]+ pattern) or that both parameters are mandatory, leaving an agent to discover identifier syntax from validation errors.

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?

"Continue a FINISHED task with another message in the same ZCode conversation" gives a specific verb (continue) plus resource (existing ZCode task/conversation), and the word "continue" implicitly separates it from a fresh-start sibling. It stops short of naming the tool used to start a new task, so the differentiation from zcode_run rests on inference.

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?

Preconditions are explicit and stateful: the task must not be running and must not be archived, which functions as a clear when-to-use / when-not-to-use boundary. It also prescribes the follow-up step ("use zcode_wait afterwards"), though it never explicitly redirects an agent to a different tool for a brand-new or still-running task.

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