Skip to main content
Glama

codex_history

Read-onlyIdempotent

Retrieve persisted conversation turns or items for owned tasks, including after an outage, using cursor paging; large records flag truncated fields.

Instructions

Page persisted turns or items for owned conversations, including after an outage. Large items identify truncated_fields; pending approval details come from codex_review_request.

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_id": "<task_id>"
    },
    "name": "codex_history"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoturns
limitNo
cursorNoNative cursor
task_idYesTask id
turn_idNo

Output Schema

NameRequiredDescriptionDefault
okYes
result_versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so safety is covered. The description adds genuine value by noting that data is persisted across outages and that large items flag truncated_fields, but it says nothing about pagination limits, ordering of results, or what happens when task_id is unknown. Solid additions, but not rich behavioral context.

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?

Two dense sentences with the primary action and the retrieval context front-loaded, and the sibling pointer placed last where it is least disruptive. The phrase 'including after an outage' is slightly oblique but earns its place by implying the persistence guarantee.

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?

Annotations cover safety and an output schema exists, so return-value detail is unnecessary. However, for a paginated history tool the description leaves the turns-vs-items distinction, cursor semantics, and ordering undefined, which are exactly the gaps the 40%-coverage schema cannot fill.

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

Parameters2/5

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

Schema description coverage is only 40%, and the description does not compensate: only the 'turns or items' enum is echoed without explaining how a turn differs from an item. The five parameters include limit (max 200), cursor, task_id and turn_id, none of which get semantics from the description beyond the schema's terse labels.

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 uses a specific verb ('Page') with a specific resource ('persisted turns or items for owned conversations') and scopes it to owned conversations, which plausibly separates it from codex_events or codex_get. It stops short of explicitly contrasting with any named sibling, so the agent must still infer the boundary.

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 two real usage signals: this is the way to retrieve persisted history, notably after an outage, and pending approval details should come from codex_review_request instead. That is an explicit alternative for a specific need, though it never says when to choose turns vs items or when a live/event-based tool would be preferable.

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