Skip to main content
Glama

ouroboros_interview

Clarify requirements interactively by starting, resuming, or answering interview questions; each response refines the project context for downstream execution.

Instructions

Interactive interview for requirement clarification. Start a new interview with initial_context, resume with session_id, or record an answer to the current question. In plugin mode, returns a delegation receipt (status=delegated_to_subagent) and the interview executes in an OpenCode Task pane — the real session_id is returned there.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cwdNoWorking directory for brownfield auto-detection. Defaults to the current working directory if not provided.
answerNoResponse to the current interview question
referencesNoBounded user-provided reference cues. Each object requires reference_id, label, and origin; url/excerpt are optional.
session_idNoSession ID to resume an existing interview
interview_idNoOptional caller-supplied id for a brand-new interview. Must match the server format 'interview_<16 lowercase hex>' and must NOT collide with an existing interview file. Only valid for the start action — supplying it together with session_id (resume) or answer is rejected with an error to prevent silent identifier hijacking; do not preserve this argument across turns. Used by the bounded auto driver to pre-allocate the id so a driver-level cancel cannot leave auto state out of sync with the persisted interview file (see Q00/ouroboros#687).
last_questionNoThe question text from the previous child session's response. In plugin mode each dispatch creates a new child session whose questions are not automatically persisted server-side. Pass the child's last question here when submitting an answer so the interview transcript preserves the real question text instead of a placeholder.
confused_termsNoExplicit domain terms the user says they do not understand. Queued on the start turn and applied only after the first answer.
initial_contextNoInitial context to start a new interview session
Behavior4/5

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

With no annotations, the description carries the burden. It discloses plugin-mode behavior (delegation receipt, OpenCode Task pane, real session_id returned there), which is a valuable trait. It lacks disclosure of normal-mode return values or persistence side effects, preventing a higher score.

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 description is two focused sentences, front-loaded with the core purpose and then the plugin-mode caveat. Every sentence contributes value, with no filler.

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?

Given 8 parameters and no output schema, the description is not fully complete. It explains plugin-mode returns but not standard-mode responses, error conditions, or the overall interaction loop. The parameter schema helps, but the main description leaves gaps.

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 description coverage is 100% with rich per-parameter text, so the baseline is 3. The main description adds meaning by mapping parameters to actions (initial_context for start, session_id for resume, answer for recording), which goes beyond the schema.

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 opens with 'Interactive interview for requirement clarification,' providing a specific verb and resource. It clearly distinguishes itself from sibling tools like ouroboros_pm_interview by specifying its focus on requirement clarification.

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 explicitly describes three invocation modes—start with initial_context, resume with session_id, or record an answer—giving clear context for usage. However, it does not compare directly to alternative tools or state when not to use it.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Q00/ouroboros'

If you have feedback or need assistance with the MCP directory API, please join our Discord server