Sora Commander

Overview Schema Source Related Servers Discussions Admin

previous_output

Reads archived output from an earlier Host session: omit session_id for a bounded metadata index, or provide an archived ID to retrieve only that session’s stored output; never replays jobs.

Instructions

Read archived logs from a PREVIOUS Host invocation; never replay.

    Without ID returns a bounded metadata index. With ID returns only
    that old session's stored output. A local Owner opt-in is mandatory.

Use to read an Owner-verified result archive from a PREVIOUS Host invocation. Omit session_id for metadata index, supply the original archived session_id for output and eligible safe-command identity. May contain sensitive stdout; never repost IDs or output without Owner verification, and never replay jobs.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "previous_output"
  }
}

Input Schema

Name	Required	Description	Default
`session_id`	No	Optional archived session ID (48 lowercase hex); omit for Owner-verified metadata index. Never disclose private IDs without Owner verification.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.2Nov 9, 2026

TDQS

A3.6/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose real behavior: an Owner opt-in is required before use, the no-ID result is a "bounded" metadata index rather than full logs, and output may contain sensitive stdout. It stops short of quantifying the bound or describing failure behavior when opt-in is absent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The two paragraphs largely duplicate each other: "never replay" appears twice, and Owner verification appears three times. The mode-selection rule and the security warning are each stated twice, so the definition is roughly twice the necessary length despite being front-loaded correctly.

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?

An output schema exists, so return values need not be described. The description covers both invocation modes, the authorization prerequisite, and the sensitivity of the payload, which is enough for a single-optional-parameter read tool. Only the meaning of "bounded" and the not-authorized case are left open.

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 100% and the schema already documents the 48-hex format, the null default, and the metadata-index behavior. The description restates that omit-vs-supply mapping and adds the notion of "eligible safe-command identity" from the archive, but contributes little syntax or meaning beyond the schema.

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?

"Read archived logs from a PREVIOUS Host invocation" gives a specific verb and resource, and the two-mode split (omit session_id → metadata index; supply it → that session's stored output) is stated explicitly. It is distinguishable from read_process_output and the live-session tools by the word "archived/PREVIOUS", though the obvious sibling previous_sessions is never named.

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 states the selection rule clearly: omit session_id for the metadata index, supply the original archived session_id for output. It also states the hard precondition (a local Owner opt-in is mandatory) and an exclusion (never replay jobs). It does not name a sibling alternative to use when the archive is not Owner-verified, which keeps it short of a 5.

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