Skip to main content
Glama
Sign In

Checkbox

by site.checkbox
OverviewDiscussionsAdmin

Record the human's answer to a manual task

answer_task

For tasks with status "manual": record the HUMAN's answer to task.question. Ask the human first and pass their words; never answer on their behalf (answers are legal attestations stored in the evidence vault). answer is one of task.question.options; yes / no also work (= confirmed / needs_change). "no" turns the task into a change you can apply.

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": {
      "task": "<task>",
      "answer": "<answer>"
    },
    "name": "answer_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoContext from the human, stored with the answer.
taskYesTask id (task_…) with status manual.
answerYesOne of the task.question.options, as the human chose.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / additionalProperties
      Previous value: -falseNew value: +true
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare the generic profile (non-readonly, non-destructive, non-idempotent, closed-world); the description adds real consequences beyond that — answers are legal attestations persisted in the evidence vault, and answering 'no' converts the task into an applicable change. It stops short of saying whether re-answering a completed task is rejected or overwrites, which matters given idempotentHint=false.

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?

Front-loaded with the scope condition, then the constraint, then the value domain — a sensible ordering with almost no filler. The parenthetical about the evidence vault is dense but load-bearing, since it justifies the 'never answer for them' rule.

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 three-parameter write tool with full schema coverage and no output schema, the description covers the caller's obligations and downstream effects well. It omits failure modes (invalid option, task already answered, wrong status) that an agent would otherwise have to discover at runtime.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description genuinely adds meaning: 'answer' accepts yes/no aliases mapped to confirmed/needs_change, a detail absent from the schema's 'one of the task.question.options' wording. The 'note' parameter is left entirely to the schema, which is acceptable given its own description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('record the HUMAN's answer to task.question') and scopes it precisely to 'tasks with status "manual"'. That scope restriction is what separates it from sibling tools like verify_task or get_task without the agent needing to open any schema.

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 an explicit precondition ('For tasks with status "manual"') and a strong when-to-use instruction: ask the human first, pass their words, never answer on their behalf. What it does not do is name the alternative tool to use for non-manual tasks (e.g. verify_task), so routing for edge cases is left implicit.

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

All Checkbox toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources