AtlasClose Governance Demo

Request capability

atlas.request_capability

[NEEDS ADMISSION: enroll, then atlas.bind_actor] Request a capability. Refusal is institutional. The result carries the primary actor block. capability is the name of the act, for example evidence.append (payload {content}), matter.read, or release:outside (consequential: it is refused unless the Human has granted it, and even then held for a Human decision). payload is a JSON object that belongs to that capability. atlas.list_capabilities shows which names you hold.

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": {
      "actor_token": "<actor_token>",
      "matter_id": "<matter_id>",
      "capability": "<capability>"
    },
    "name": "atlas.request_capability"
  }
}

Input Schema

Name	Required	Description
`payload`	No	Details of the requested act, as a JSON object. Describing an act does not authorize it.
`matter_id`	Yes	Id of the matter you are admitted to (returned by atlas.bind_actor). Optional when you are bound to exactly one matter.
`capability`	Yes	Name of the act, for example 'evidence.append' or 'release:outside'. atlas.list_capabilities shows what you hold and what you cannot do.
`actor_token`	Yes	Your credential from atlas.enroll or atlas.authenticate. Send it on every call after enrolling.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 17, 2026

TDQS

A3.9/5.0

Behavior4/5

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

With only readOnlyHint=false in the annotations, the description carries real behavioral weight: it discloses that refusal is institutional, that the result carries the primary actor block, and that release:outside is consequential — refused unless the Human has granted it and even then held for a Human decision. This is meaningful policy context beyond the annotation; it only lacks return-format/reversibility detail.

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 prerequisite bracket and the capability examples are front-loaded and every clause carries information. The stacked parentheticals make the middle dense, but there is no filler or repetition.

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 mutation tool with no output schema and minimal annotations, the description supplies the missing pieces: admission prerequisites, what the result carries, and the escalation semantics of a consequential capability. An agent could call this correctly from the description alone; only general error/permission behavior is unstated.

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%, so all four parameters are already documented, and the description largely restates them (capability = name of the act, payload = JSON object belonging to that capability). It adds a small amount of value by tying a capability name to an example payload shape (evidence.append -> {content}), but not enough to exceed the baseline.

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 a specific verb+resource ('Request a capability') with concrete examples of what a capability name looks like (evidence.append, matter.read, release:outside). It partially differentiates from siblings by naming atlas.list_capabilities as the read-side counterpart. It stops short of a crisp one-line scope statement, but an agent can identify the operation.

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?

Prerequisites are stated explicitly and front-loaded ('NEEDS ADMISSION: enroll, then atlas.bind_actor'), and the description names atlas.list_capabilities as the way to see which names you currently hold. It does not spell out general when-not-to-use conditions beyond the release:outside special case.

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?