New LLM Release Tracker — buy per-query in-session (llmwatch)

data_session_open

Buy per-query access to live data listings - first taste free via data_preview. Listing: llmwatch: New LLM Releases & Serving Availability (0.01 USDC/query (max 20 queries/session)). Open a prepaid session, then fund and query.

Input Schema

TableJSON Schema

Name	Required	Description
`listing_id`	No	UUID of the listing. Provide exactly one of listing_slug or listing_id.
`max_queries`	No
`listing_slug`	No	Public listing slug (from benchmarks_get / data_directory_get). Provide exactly one of listing_slug or listing_id.
`open_tx_hash`	No
`buyer_address`	No	Buyer EVM address. Optional: defaults to your own platform wallet when omitted.
`proof_escrow_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedSep 7, 2026

addedInput schema / description

Added value: +"MCP-only input for ``data_session_open``.\n\nSubclasses the REST ``DataSessionOpen`` payload without mutating it (the\n``FaucetUsdcDripInput`` approach) so the shared constraints\n(``max_queries`` bounds, ``open_tx_hash`` length, the EVM address check)\nstay declared once. Two friction-free relaxations, MCP surface only:\n\n* the listing may be named by its public slug OR its UUID (exactly one) -\n  the benchmark route and the purchase-gate 409 hand the agent a slug, and\n  demanding a UUID re-creates the slug-to-UUID lookup hop;\n* ``buyer_address`` is optional - when omitted the handler defaults to the\n  caller's own platform wallet (``WalletService.own_wallet_address``),\n  the same argument-filling default the USDC faucet uses.\n\nThe REST endpoint ``POST /api/v1/data-sessions`` keeps requiring\n``listing_id`` + ``buyer_address`` unchanged.\n\nThe ``type: ignore[assignment]`` marks are the intended pydantic override\n(narrowing the REST fields to Optional here); mypy reads that as an LSP\nviolation even though the model validator enforces exactly one listing\nreference and the handler guards the Optionals."

addedInput schema / properties / buyer_address / anyOf

Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / buyer_address / default
```
Added value: +null
```

addedInput schema / properties / buyer_address / description

Added value: +"Buyer EVM address. Optional: defaults to your own platform wallet when omitted."

removedInput schema / properties / buyer_address / type
```
Removed value: -"string"
```

addedInput schema / properties / listing_id / anyOf

Added value: +[
+  {
+    "format": "uuid",
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]

addedInput schema / properties / listing_id / default
```
Added value: +null
```

addedInput schema / properties / listing_id / description

Added value: +"UUID of the listing. Provide exactly one of listing_slug or listing_id."

removedInput schema / properties / listing_id / format
```
Removed value: -"uuid"
```
removedInput schema / properties / listing_id / type
```
Removed value: -"string"
```

addedInput schema / properties / listing_slug

Added value: +{
+  "anyOf": [
+    {
+      "minLength": 1,
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Public listing slug (from benchmarks_get / data_directory_get). Provide exactly one of listing_slug or listing_id.",
+  "title": "Listing Slug"
+}

removedInput schema / required

Removed value: -[
-  "listing_id",
-  "buyer_address"
-]

changedInput schema / title

Previous value: -"DataSessionOpen"New value: +"DataSessionOpenInput"

First observedSep 6, 2026

TDQS

B3.3/5.0

Behavior3/5

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

The description discloses the key monetary behavior that annotations cannot express: this costs real money (0.01 USDC/query) and carries a session cap (20 queries/session), and it is a state-changing purchase. However, it does not disclose what happens after opening (what is returned), whether the session requires immediate funding, or what prerequisites the escrow/tx-hash parameters imply. No contradiction with the annotations (all false hints are consistent with a mutating purchase action).

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?

Three compact sentences, each earning its place: the core buy action, the concrete listing with pricing/cap, and the follow-on lifecycle. The most decision-relevant facts (payment, free-alternative routing) are front-loaded. Minor structural improvement would be separating the listing-specific detail from the general tool behavior, but it is efficient overall.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a money-touching tool with 6 parameters, no output schema, and implicit on-chain prerequisites, the description is too thin. It omits the return value (e.g., session identifier), the role of open_tx_hash and proof_escrow_id in the purchase flow, and wallet prerequisites beyond the schema's own mention. The verbose schema-description block focuses on pydantic/mypy developer concerns rather than agent-facing invocation guidance, so it does not fill these gaps.

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?

The description adds genuine value beyond the schema by revealing the listing-specific constraint that max_queries is effectively capped at 20 per session despite the schema allowing up to 50, and by giving per-query pricing. However, schema coverage is only 50%, and the description does not compensate for the undocumented parameters: open_tx_hash, proof_escrow_id, and max_queries semantics remain unexplained.

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 action ('Buy per-query access' / 'Open a prepaid session') on a clear resource (live data listings). It differentiates itself from data_preview by marking that tool as the free alternative. However, it does not distinguish itself from the other data_session_* siblings (fund, query, attach_escrow), leaving the session-lifecycle relationship to inference.

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?

The description gives useful context: for a free taste use data_preview, and after opening a session 'then fund and query' describes the sequence. But it never names the alternative sibling tools (data_session_fund, data_session_query, data_session_attach_escrow) and states no exclusion criteria for when this tool should not be used.

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

All New LLM Release Tracker — buy per-query in-session (llmwatch) 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?