Skip to main content
Glama

Respond to work

respond

Answer a work item with text for the learner and optional tool calls, then receive the next item in the same conversation or a turn_complete status.

Instructions

Answer a work item the way a model would: text for the learner (or the task), and/or calls to the tools listed in the work item. Returns the next work item in the same conversation when the app needs you again right away (for example with tool results), or status "turn_complete".

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": {
      "work_id": "<work_id>"
    },
    "name": "respond"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoYour message (markdown).
work_idYesThe workId from wait_for_work or a previous respond.
tool_callsNoTool calls, run in order. Use only tools listed in the work item.
wait_secondsNoHow long to wait for the follow-up (default 30).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the generic annotations, it usefully discloses the continuation protocol: the call may immediately return another work item, including one carrying tool results, or finish with turn_complete. It does not cover error, timeout, or failed tool-call behavior, but the normal control flow is well explained.

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?

Two compact sentences front-load the operation and then explain the possible continuation outcomes. The phrase 'the way a model would' is vague and adds little, preventing the wording from being completely tight.

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?

Together with the fully described schema, the definition covers the required identifier, response modes, tool restriction, and return behavior despite having no output schema. Explicit lifecycle guidance connecting acquisition of work, responding, immediate follow-ups, and subsequent waiting would make this protocol tool easier to use without inference.

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 the schema already documents all four parameters, including work_id sources, ordered tool calls, and wait_seconds. The description adds some audience and combination context for text and tool_calls, but only modest meaning beyond those structured descriptions.

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 clearly states the action and resource: answering a work item with learner/task text and/or permitted tool calls. It does not explicitly differentiate respond from siblings such as wait_for_work or read_work.

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?

The work-item context is clear, and restricting calls to tools listed in that item provides actionable invocation guidance. However, the description does not explicitly explain when to use respond versus waiting for or reading work, or what to do after receiving turn_complete.

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