hive

Overview Schema Source Related Servers Discussions Admin

question_ask

Record an open question for the human, scoped to your project, with a default answer; choice or free text. Dedupe by todo id or PR number and get woken when answered.

Instructions

Record an open question for the human, keyed to this project and to you as the asker. kind=choice takes 2-4 options (each label, description, recommended; exactly one recommended) and a header of 12 characters or fewer; kind=free_text takes just the question and header. Every question carries default_answer: for a choice it is the recommended option's label. Pass ref (a todo id or PR number) to dedupe: asking again with a ref that already has a PENDING question in this project updates that row instead of adding one. The receipt lists other pending questions in this project that look similar (same normalized text, or at least half their longer words shared), so you can question_update one instead. The record is only stored: put the question to the human yourself, in your own turn. You must be a session an answer can be woken back to. When the question is answered, an ordinary wake carrying the answer is queued to you; read the record with question_get.

Input Schema

TableJSON Schema

Name	Required	Description
`ref`	No
`kind`	Yes
`header`	Yes	12 characters or fewer.
`options`	No	Required for choice, forbidden for free_text.
`question`	Yes
`default_answer`	Yes	What you do if unanswered. For a choice, the recommended label.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`created`	Yes
`hive_notice`	No
`question_id`	Yes
`similar_question_ids`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.11.5Oct 15, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false), and the description adds rich behavior beyond them: the record is only stored and the agent must surface the question itself, the caller must be a wakeable session, an ordinary wake is queued on answer, and ref-with-pending-question updates rather than inserts. This is substantial disclosure.

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?

Dense and front-loaded with the core purpose, and almost every clause adds actionable information (dedupe, default_answer, wake-on-answer). It is long and clause-heavy, but there is little filler to cut.

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

Completeness5/5

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

An output schema exists so return values need not be explained, and the description nonetheless covers the full lifecycle: creation, dedupe, human presentation, wake-on-answer, and follow-up read. Nothing material is missing for correct invocation.

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 50%, so the description must compensate, and it does: it defines kind=choice vs free_text, the 2-4 option shape with exactly one recommended, the 12-character header limit, default_answer semantics per kind, and ref as a dedupe key. It adds meaning over the schema's field descriptions.

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?

Opens with a specific verb+resource ('Record an open question for the human'), scoped to project and asker. It is clearly separable from siblings: question_update updates an existing row, question_get reads it, question_answer answers it. An agent can route correctly without opening other schemas.

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?

Gives concrete conditional guidance: use kind=choice vs free_text, pass ref to dedupe, and 'so you can question_update one instead' routes to an alternative. It also instructs the agent to put the question to the human itself and to read via question_get. Missing only explicit when-not-to-use framing, hence not a 5.

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