OpenMark

Get benchmark results

get_results

Status of a benchmark job, and once completed the ranked results (score, stability, cost per run, latency) plus a recommendation for the chosen objective and quick picks for the others.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`job_id`	Yes
`tolerance`	No	Score points below the top score that still count as good enough
`optimize_for`	No	accuracy (same order as the app's results table): best score, then cheapest, then fastest. cost / speed / stability: cheapest / fastest / most consistent model within `tolerance` points of the top score	accuracy

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 19, 2026

changedInput schema / properties / optimize_for / description

Previous value: -"accuracy: best score, cheapest on ties. cost / speed / stability: cheapest / fastest / most consistent model within `tolerance` points of the top score"New value: +"accuracy (same order as the app's results table): best score, then cheapest, then fastest. cost / speed / stability: cheapest / fastest / most consistent model within `tolerance` points of the top score"

Changed2 schema fields changedOct 18, 2026

addedInput schema / properties / optimize_for

Added value: +{
+  "default": "accuracy",
+  "description": "accuracy: best score, cheapest on ties. cost / speed / stability: cheapest / fastest / most consistent model within `tolerance` points of the top score",
+  "enum": [
+    "accuracy",
+    "cost",
+    "speed",
+    "stability"
+  ],
+  "type": "string"
+}

addedInput schema / properties / tolerance

Added value: +{
+  "default": 2,
+  "description": "Score points below the top score that still count as good enough",
+  "maximum": 50,
+  "minimum": 0,
+  "type": "number"
+}

First observedOct 18, 2026

TDQS

B3.2/5.0

Behavior3/5

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

No annotations are present, so the description carries the full behavioral burden. It usefully discloses the conditional behavior (status before completion, ranked results after) and the returned fields, but it omits whether the call is read-only, authentication or permission needs, error behavior for invalid job IDs, and rate limits.

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 definition is a single, front-loaded sentence that moves from status to completed results to extras. It is dense but contains no filler, though the parenthetical list and 'the others' phrasing make it slightly run-on.

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

Completeness3/5

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

There is no output schema, so the description appropriately lists returned fields (score, stability, cost per run, latency, recommendation, quick picks). However, it leaves gaps around status values, error handling, and how it relates to sibling tools for polling or running benchmarks, making it only adequate for correct agent use.

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 67%, with detailed enum and tolerance descriptions already in the schema. The description adds little parameter meaning beyond alluding to 'chosen objective' and 'the others', and does not compensate for the undocumented job_id parameter.

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 the specific resource (a benchmark job) and what is returned: status, ranked results with named metrics, a recommendation, and quick picks. It is not a tautology and implicitly distinguishes this from run_benchmark by focusing on retrieval, but it does not explicitly name or differentiate against siblings like watch_task.

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

Usage Guidelines2/5

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

There is no explicit guidance on when to use this tool versus alternatives such as watch_task or run_benchmark. The phrase 'once completed' hints at polling after a job finishes, but no conditions, prerequisites, or exclusions are provided.

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

All OpenMark 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?