AtlasClose Governance Demo

Run record

atlas.run_record

Read-onlyIdempotent

[EVALUATION: needs a configured model provider] Reconstruct one governed run from its preserved inputs and raw generations. Send the run id Atlas gave you. An unknown or altered run fails closed. This does not list other runs and does not read the Court docket.

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": {
      "run_id": "<run_id>"
    },
    "name": "atlas.run_record"
  }
}

Input Schema

Name	Required	Description	Default
`run_id`	Yes	The run id returned by atlas.use.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 17, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare the safe read-only, idempotent, non-destructive profile, but the description adds real behavioral context beyond them: the model-provider prerequisite and the fail-closed behavior on an unknown or altered run id. These are meaningful traits an agent could not infer from the annotations alone.

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 text is tightly packed and front-loads the key prerequisite before the action, then the exclusions. The bracketed evaluation marker is slightly awkward but functionally informative, and no sentence is wasted.

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?

For a single-parameter, read-only tool with no output schema, the description covers the prerequisite, the input source, the failure mode, and the scope boundaries. What it omits (return shape) is not required given there is no output schema, but a note on what the reconstruction yields would help.

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?

With a single parameter at 100% schema description coverage, the schema already documents run_id as 'the run id returned by atlas.use.' The description largely restates this provenance ('the run id Atlas gave you') without adding format, validation, or example detail, so the baseline 3 is appropriate.

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 names a specific verb and resource ('Reconstruct one governed run') and clarifies it operates on a single run's preserved inputs and raw generations. It explicitly distinguishes itself from adjacent capabilities by stating it 'does not list other runs and does not read the Court docket,' so an agent can separate it from list/read 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 supplies an operational precondition ('needs a configured model provider') and directs the caller to 'Send the run id Atlas gave you,' which ties invocation to prior use of atlas.use. It also gives exclusions (no listing, no docket), though it never names the sibling tools an agent should use instead for those cases, keeping it 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 AtlasClose Governance Demo 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?