Santismm Knowledge — Harness Engineering, Agentic AI & Governance

List the AI benchmarks tracked by benchmarks.santismm.com

list_benchmarks

Read-onlyIdempotent

List every benchmark in the AI Agent Benchmarks catalogue (agentic benchmarks with SOTA, saturation and headroom) and in the radar's complementary list (vision, long context, factuality, instruction following, language). Use this to find a benchmark slug; then call get_benchmark.

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": "list_benchmarks"
  }
}

Input Schema

Name	Required	Description	Default
`list`	No	Restrict to the agentic catalogue or the complementary list. Omit for both.

Output Schema

Name	Required	Description	Default
`count`	Yes
`results`	Yes
`dataset_version`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 6, 2026
- removedOutput schema / properties / results / items / properties / sota_normalized / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
- addedOutput schema / properties / results / items / properties / sota_normalized / type
```
Added value: +[
+  "number",
+  "null"
+]
```
AddedOct 17, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile needs no repetition. The description adds genuine behavioral context by explaining what the catalogue actually contains (SOTA, saturation and headroom figures) and that the two lists are distinct datasets. Pagination and result ordering are unstated, but the output schema exists to carry return shape.

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?

Two sentences, front-loaded with the action and scope, then the follow-up step. No filler, no restatement of the title, and every clause carries information the agent needs.

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?

With one optional enum parameter, full schema coverage, complete annotations and an output schema, the remaining burden on the description is small and it is fully met: what the tool returns conceptually, how the two lists differ, and what to call next.

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?

Schema coverage is 100% and the enum already documents 'catalog' vs 'complementary' plus the omit-for-both default, so the schema does the baseline work. The description goes beyond the bare enum by describing what each list actually holds, which helps the agent choose a value semantically rather than by label alone.

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 opens with a specific verb and resource ('List every benchmark in the AI Agent Benchmarks catalogue') and immediately enumerates the two content domains covered (agentic SOTA/saturation/headroom vs. vision, long context, factuality, instruction following, language). An agent can distinguish this from the many other list_* siblings without opening a 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 states the concrete use case ('find a benchmark slug') and names the exact follow-up call ('then call `get_benchmark`'), which is real routing guidance. It does not say when not to use it or how it differs from `search`, so it stops short of full when/when-not coverage.

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

All Santismm Knowledge — Harness Engineering, Agentic AI & Governance 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.