Codex Reset Tracker

Codex reset announcements

get_codex_reset_announcements

Read-onlyIdempotent

Codex usage-limit reset announcements recorded by tokenusage.dev's Reset Alerts from @thsottiaux's public posts on X, newest first (at most 50): each post's link, when it was posted, when this site recorded it and resetType, plus when the monitor last checked X successfully. resetType is automatic, banked or both; null means recorded before Reset Alerts recorded reset types. A banked reset grant saves a reset for eligible users to apply later and does not itself refill limits. An announcement may describe a forthcoming event or one already completed; a post is not proof that any account's limit was reset. Open its url for the exact wording and eligibility. Only @thsottiaux is watched. Unofficial, not affiliated with OpenAI. Source: https://tokenusage.dev/resets

Input Schema

Name	Required	Description	Default
`limit`	No	How many announcements to return, newest first: 1 to 50, default 10.

Output Schema

Name	Required	Description
`resets`	Yes	Newest first.
`source`	Yes	The fixed credit URL, https://tokenusage.dev/resets. When showing the data to other people, show Data: tokenusage.dev linked to this URL on the same screen or in the same message. Personal use needs no visible credit. API and MCP relays must retain source and pass on this credit condition.
`generatedAt`	Yes	When tokenusage.dev read this data, ISO 8601 UTC. The server caches it for up to 15 seconds.
`lastPolledAt`	Yes	The monitor's latest successful fetch of @thsottiaux's X timeline, checks that found no new posts included, ISO 8601 UTC; null before the first, or when an older record lacks it. It is not a sign that classification or alert delivery is working.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 10, 2026

addedOutput schema / properties / resets / items / properties / resetType

Added value: +{
+  "description": "The monitor's classification of the post: automatic is a direct usage-limit reset with no saved reset; banked is a reset grant saved for eligible users to apply later; both announces both types. Both classifier calls must give the same type. Null means recorded before Reset Alerts recorded reset types. This is not proof that any account's limit was reset.",
+  "enum": [
+    "automatic",
+    "banked",
+    "both",
+    null
+  ],
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / properties / resets / items / required

Previous value: -[
-  "postId",
-  "url",
-  "postedAt",
-  "detectedAt"
-]New value: +[
+  "postId",
+  "url",
+  "postedAt",
+  "detectedAt",
+  "resetType"
+]

First observedOct 9, 2026

TDQS

A4/5.0

Behavior5/5

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

Annotations already cover readOnlyHint, idempotentHint, destructiveHint, and openWorldHint, so the bar is lower; the description still adds substantial context beyond them. It explains resetType values (automatic, banked, both, null), clarifies that a banked reset does not itself refill limits, warns that an announcement may be forthcoming or completed and is not proof of a reset, notes that only @thsottiaux is watched, and discloses that the source is unofficial and not affiliated with OpenAI.

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?

The description is front-loaded with the core purpose and is dense with useful information, but it runs long and could be tightened slightly. Every sentence carries meaning, though some readers may find the resetType and banked-reset explanation verbose relative to the single-parameter lookup.

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?

For a read-only tool with one optional parameter and an output schema, the description supplies everything an agent needs: source, uniqueness of the watched account, field meanings, caveats about interpretation, and a pointer to the url for exact wording and eligibility. Nothing critical is missing.

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 description coverage is 100% – the limit parameter already documents its range (1–50), default (10), and ordering (newest first). The description echoes 'newest first (at most 50)' but adds no additional syntax, format, or behavioral detail beyond what the schema provides, so the baseline 3 is appropriate.

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 states a specific verb (get) and resource (Codex reset announcements), plus the exact source (@thsottiaux's public posts on X) and ordering (newest first, at most 50). It clearly distinguishes what data is returned, but it never mentions the sibling tool get_codex_reset_calendar or explains how the two differ, so an agent must infer the choice.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the resource name and the detailed semantics of resetType and banked resets, but there is no explicit when-to-use/when-not guidance and no alternative tool named. The caveat that 'a post is not proof that any account's limit was reset' hints at interpretation limits, yet it does not route the agent between available options.

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

All Codex Reset Tracker tools Inspect

Try in Browser

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.