Skip to main content
Glama

Authorize Action

atlas_authorize

Request authorization before deleting, deploying, spending, or sending. Atlas checks proposed actions and effects against the delegation chain, returning permit, deny, or escalate with a receipt ID.

Instructions

Ask for authorization BEFORE doing anything consequential (deleting data, deploying, spending, sending). Atlas checks the action and its effects against the signed delegation chain and returns permit, deny or escalate with a receipt_id. Do not perform the action unless the decision is permit (or escalate that a human later approved).

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": {
      "agent": "<agent>",
      "principal": "<principal>",
      "requested_action": "<requested_action>",
      "effects": "<effects>",
      "delegation_chain": "<delegation_chain>"
    },
    "name": "atlas_authorize"
  }
}

Input Schema

NameRequiredDescriptionDefault
agentYesYour agent id, as named in the last delegation grant
effectsYesEvery effect the action will have. Be complete and honest.
principalYesThe human or system that originally delegated authority
delegation_chainYesGrant ids, root first (principal -> ... -> you)
requested_actionYesAction name, e.g. db.delete

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare it is not read-only, not idempotent, and not destructive; the description adds real value by disclosing the decision model (checks action and effects against the signed delegation chain) and the three possible verdicts plus a receipt_id. It does not cover latency, whether repeated calls are safe or cached, or what the receipt is used for, so it falls short of full disclosure.

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, both load-bearing. The gating instruction and the precondition are front-loaded, and there is no redundant restatement of the tool name or schema.

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?

With no output schema, the description correctly carries the return-value burden by naming the three verdicts and receipt_id. It stops short of explaining what to do with the receipt afterwards (e.g. checking status) or how escalate approvals are confirmed, which is the only remaining gap for a five-parameter authorization gate.

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 each parameter is already documented in the schema. The description only loosely ties requested_action, effects, and delegation_chain to the decision process without adding format or syntax detail beyond what the schema provides, so the baseline 3 applies.

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?

States a specific verb and resource: it requests authorization for a described action and evaluates it against a signed delegation chain. It also names the outputs (permit, deny, escalate, receipt_id), which makes its role clearly distinct from siblings like atlas_commit_effect and atlas_receipt_status.

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

Usage Guidelines5/5

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

Explicitly says when to call it ('BEFORE doing anything consequential') with concrete trigger examples (deleting, deploying, spending, sending). It also states the when-not/blocking rule: do not proceed unless the decision is permit or an approved escalate, which is exactly the gating guidance an agent needs.

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