NL;NL Labs Exchange results

One model over time

get_model_history

Read-onlyIdempotent

Use to follow one model on one job over time (for example, has it got cheaper or worse). Returns its published days: right answers, items, cost per 1,000 right in US dollars and IPD (right answers per dollar). On Extract, every row names its test; the answer says what the two tests are, and rows before and after 4 Nov come from different tests. Fields: cost_per_1000_right_usd and ipd are exact; cost_shown and ipd_shown are how the page shows them. assembled_by_us is 1 when the answer was assembled by us, else 0. A count marked "not published for this model" is not published for that model.

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": {
      "job": "<job>",
      "model": "<model>"
    },
    "name": "get_model_history"
  }
}

Input Schema

Name	Required	Description	Default
`job`	Yes	Job id.
`model`	Yes	Model or system name for that job, e.g. GPT-6 Luna, Claude Haiku 5.5, NL;NL Desk (a system. Not open yet.).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 10, 2026

changedInput schema / properties / job / description

Previous value: -"Job id (see list_jobs)."New value: +"Job id."

changedInput schema / properties / model / description

Previous value: -"Model or system name for that job, from list_jobs, e.g. GPT-6 Luna, Claude Haiku 5.5, NL;NL Desk (a system. Not open yet.)."New value: +"Model or system name for that job, e.g. GPT-6 Luna, Claude Haiku 5.5, NL;NL Desk (a system. Not open yet.)."

First observedNov 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, yet the description adds real disclosure beyond them: the exact-vs-displayed distinction between cost_per_1000_right_usd/ipd and cost_shown/ipd_shown, the meaning of assembled_by_us, the 'not published for this model' sentinel, and the caveat that on Extract rows before and after 4 Nov come from different tests. That last point is a genuine interpretation hazard the agent would otherwise miss. It says nothing about rate limits or freshness/pagination, keeping it off a 5.

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 purpose is front-loaded and the later sentences are dense but largely load-bearing given there is no output schema. Minor waste remains: the closing sentence, 'A count marked "not published for this model" is not published for that model,' restates itself almost verbatim.

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 no output schema, the description correctly takes on the return-value burden, enumerating the published fields and their exactness semantics plus the test-discontinuity caveat. The one loose end is 'items' in the returned list, which is never defined, and there is no hint of ordering or row count.

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% and the enum plus model-name example are already documented in the schema, so the description's 'one model on one job' phrasing is reinforcement rather than new meaning. Baseline 3 is appropriate when the schema carries parameter semantics.

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?

The description gives a specific verb-and-resource pair: it follows a single model on a single job over time, and it even names the question it answers ('has it got cheaper or worse'). Combined with the required job/model pair in the schema, an agent can distinguish this from get_day_results (a day slice) and list_jobs (a catalog) without opening either schema.

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 opens with an explicit 'Use to' clause and supplies a concrete motivating scenario, so the when-to-use case is clear. It does not state exclusions or name an alternative for cross-model or per-day comparisons, so it falls 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.

All NL;NL Labs Exchange results 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?