Skip to main content
Glama

Send Codex review comments as the next stage of the same session

dsh_continue_task

Continue a live delegated task in the same session so prior context persists; submit a review to start a new numbered stage without overwriting earlier stage evidence.

Instructions

Continues the SAME live session so the model still has its earlier work in context. Refuses unknown taskIds, a stage already in flight, cancelled tasks, tasks whose runtime died, and any stage after shutdown. Each stage gets its own number and its own result; earlier stage evidence is never overwritten.

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>",
      "review": "<review>"
    },
    "name": "dsh_continue_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalNoRestate the stage goal if it differs from the original.
reviewYesCodex's review of the previous stage, including what failed and what to change.
taskIdYes
acceptanceNoAcceptance for the new stage.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.8

TDQS

A4.1/5.0
Behavior5/5

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

Beyond the annotations, the description explains that the live session context is preserved, enumerates several refusal states, and clarifies that each stage has its own number and result without overwriting earlier evidence. That materially improves the agent's ability to predict behavior.

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?

The definition is three tight sentences: purpose first, refusal conditions second, and stage-result behavior third. No sentence is wasted, and the most important constraint is front-loaded.

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?

For a non-idempotent mutation-style tool with annotations and no output schema, the description covers purpose, preconditions, and result/state semantics well. It stops short of explaining how the per-stage result is later retrieved, but that is a minor gap.

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 75%, with goal, review, and acceptance described in the schema; taskId is undocumented. The description adds stage-level context but does not explain taskId expectations or add meaning beyond the schema for the other 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?

The description states a specific action: continuing the same live session by adding a reviewed stage. It clearly distinguishes continuation from a fresh session via 'SAME live session' and context retention, though it does not name a specific sibling alternative.

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?

It gives strong when-not guidance by listing refusal conditions: unknown taskIds, in-flight stages, cancelled tasks, dead runtimes, and shutdown. The when-to-use case is implied by continuing the SAME live session, but no explicit sibling alternative is named.

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