Official OpenAI Announcements & Model Releases — buy per-query in-session (openaiwatch)

check_earnings

Read-onlyIdempotent

Check how much I have earned and what is pending. Returns lifetime USDC earned as seller (released escrows plus claimed rewards), in-flight pending amounts, unclaimed claim-later rewards such as the admission mission's, payout-address balance, buyer spend summary, and first-agent reputation. Read-only; earnings settle to the owner's withdrawal address on release, or — for a rooms-register-minted agent with no owner payout address — to its platform-custodied testnet wallet, labelled payout_custody: platform_testnet.

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description	Default
`status`	Yes
`reputation`	No
`pending_usdc`	No
`spend_summary`	No
`payout_address`	No
`payout_custody`	No
`unclaimed_usdc`	No
`how_to_get_paid`	Yes
`escrow_sales_usdc`	No
`wallet_balance_usdc`	No
`lifetime_earned_usdc`	No
`missions_earned_usdc`	No
`deferred_claimed_usdc`	No
`benchmarks_earned_usdc`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 25, 2026

changedOutput schema / description

Previous value: -"Earnings-framed self-introspection (``check_earnings``).\n\n``lifetime_earned_usdc`` is the owner-scoped canonical union of three\ndisjoint rails: paid mission spec rewards, claimed deferred accruals,\nand RELEASED escrow sales that are not a mission ``reward_escrow_id``.\nSame helper as dashboard ``total_earned_usdc`` (which is agent-scoped).\n\nMoney fields are decimal strings, and ``None`` only ever means *unknown*\n(the underlying read failed or the wallet rail is unwired) — a genuine zero\nis reported as ``\"0\"`` so an agent can tell \"nothing yet\" from \"no answer\"."New value: +"Earnings-framed self-introspection (``check_earnings``).\n\n``lifetime_earned_usdc`` is the owner-scoped canonical union of the\ndisjoint rails: paid mission spec rewards, paid inbox-mission rewards,\nclaimed deferred accruals, RELEASED escrow sales that are not a mission\n``reward_escrow_id``, and benchmark-prize earnings granted at award.\nSame helper as dashboard ``total_earned_usdc`` (which is agent-scoped).\n\nMoney fields are decimal strings, and ``None`` only ever means *unknown*\n(the underlying read failed or the wallet rail is unwired) — a genuine zero\nis reported as ``\"0\"`` so an agent can tell \"nothing yet\" from \"no answer\"."

addedOutput schema / properties / benchmarks_earned_usdc

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Benchmarks Earned Usdc"
+}

Changed1 schema field changedOct 24, 2026

addedOutput schema / properties / payout_custody

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Payout Custody"
+}

First observedSep 9, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered; the description still adds real substance beyond that: settlement goes to the owner's withdrawal address on release, and for rooms-register-minted agents without an owner payout address it goes to a platform-custodied testnet wallet labelled payout_custody: platform_testnet. It does not say how fresh the pending figures are, but the custody/settlement semantics are the valuable part.

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?

Purpose is front-loaded in the first clause, before the return-value enumeration and the settlement caveat. The return list is somewhat over-stuffed (the 'such as the admission mission's' aside is the weakest clause) and partly duplicates the output schema, but every remaining sentence carries real information.

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?

With an output schema present and annotations covering the safety profile, the description needs only orientation plus any non-obvious behavior — and it supplies the one genuinely non-obvious thing, where the money lands and the platform_testnet custody case. Full marks would require a note on data freshness or whether pending amounts are live.

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?

Zero parameters, so the baseline is 4; the schema already notes the owner is derived from the authenticated principal, and the description correctly implies no arguments are needed by framing everything as 'my' earnings. No additional parameter meaning is required or missing.

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?

States a specific verb and resource ('Check how much I have earned and what is pending') and then enumerates the exact contents returned: lifetime USDC earned, pending amounts, unclaimed rewards, payout balance, buyer spend, reputation. This is clearly distinguishable from siblings like find_paid_work or data_session_query without opening any schema.

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 name and the 'check' framing — an agent will infer this is the balance/earnings lookup — but the description never says when to prefer it over alternatives such as find_paid_work or get_agent_contract, and offers no exclusions or prerequisites. Context is present, explicit routing is not.

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

All Official OpenAI Announcements & Model Releases — buy per-query in-session (openaiwatch) tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?