Nerf Watch

Nerf Watch scores

get_nerfwatch_scores

Read-onlyIdempotent

Latest public Nerf Watch scores, previous runs, changes and baselines for at most 100 models, ordered by provider, name and model id. No arguments. Histories are available through get_nerfwatch_history. Scores and changes are rounded to two decimals; comparisons are within one suite version. A lower score is a lower score on this suite, not proof that a provider changed a model. Unofficial, not affiliated with OpenAI or Anthropic. Source: https://tokenusage.dev/nerfwatch

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_nerfwatch_scores"
  }
}

Input Schema

Name	Required	Description	Default
No arguments

Output Schema

Name	Required	Description
`models`	Yes	Models in source order: provider, name and model id; empty before the first run.
`source`	Yes	The fixed credit URL, https://tokenusage.dev/nerfwatch. 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.
`flatPoints`	Yes	An absolute change versus baseline at or below this returned setting is flat.
`generatedAt`	Yes	When the cached data was read, ISO 8601 UTC; the cache TTL is 300 seconds from read start.
`baselineDays`	Yes	The UTC-day window before each latest run used for its baseline; this is the returned setting, not a fixed client assumption.
`dataUpdatedAt`	Yes	When the newest retained run was stored, ISO 8601 UTC; null without runs. This is distinct from response generation time.
`minBaselineRuns`	Yes	The minimum number of same-suite runs needed for a baseline; this is the returned setting.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Beyond the annotations, it discloses the 100-model limit, ordering, rounding to two decimals, within-suite-version comparisons, and a key interpretation caveat that a lower score is not proof a provider changed a model. These are substantive behavioral details that help an agent avoid overreading the results.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with what the tool returns and its ordering, then follows with the no-argument fact, the sibling alternative, and interpretation caveats. Every sentence adds useful information, and there is no redundant repetition of schema or annotation details.

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?

Given zero parameters, rich annotations, and an output schema, the description supplies the remaining context an agent needs: result scope, ordering, limits, sibling routing, rounding/comparison semantics, and a caution about interpreting changes. It does not need to explain return values because an output schema exists.

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?

The tool has zero parameters, so parameter semantics are inherently minimal. The description confirms 'No arguments,' which is consistent with the empty schema, and the baseline for a zero-parameter tool is 4.

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 states exactly what is returned: latest public Nerf Watch scores, previous runs, changes, and baselines, capped at 100 models and ordered by provider, name, and model id. It also explicitly distinguishes the sibling tool by saying histories are available through get_nerfwatch_history.

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 clearly indicates this is the latest-scores endpoint and routes history requests to get_nerfwatch_history. It does not explicitly state the full when-to-use/when-not-to-use matrix, but the alternative is named and the no-argument nature is clear.

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

All Nerf Watch 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.