Skip to main content
Glama

Check Receipt Status

atlas_receipt_status
Read-onlyIdempotent

Check an Atlas receipt's status—ready, pending human approval, rejected, denied, committed, expired, or revoked—to confirm whether an action can proceed or needs escalation.

Instructions

Check a receipt: ready, pending_approval (escalated, waiting for a human), rejected, denied, committed, expired, or revoked (a grant behind it was revoked). Approval can only be given by a human through the atlas-mcp CLI, never through this server.

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": {
      "receipt_id": "<receipt_id>"
    },
    "name": "atlas_receipt_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
receipt_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false, openWorldHint=false), so the description's added value is the state-machine semantics: what pending_approval and revoked actually mean, and that escalation requires out-of-band human action. It does not mention auth requirements or rate limits, but the workflow-level context it supplies exceeds what the annotations convey.

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?

Front-loaded with the action, then a compact parenthetical enumeration where each status definition earns its place. The one inefficiency is the dense run of nested parentheses that makes the status list slightly harder to scan than a short list would be.

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 one-parameter read-only tool with no output schema, the description supplies the crucial information an agent needs to interpret the response: the full status vocabulary and the human-approval escape hatch. The only real omission is any detail about the receipt_id input itself.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the single required parameter receipt_id is a bare string with no documentation. The description says 'a receipt' but never explains where receipt_id comes from, its format, or what happens for an unknown id — so it fails to compensate for the schema gap.

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 plus resource ('Check a receipt') and then enumerates every possible state with meanings, including 'pending_approval (escalated, waiting for a human)' and 'revoked (a grant behind it was revoked)'. An agent can immediately tell this is a read-only status lookup, distinct from the sibling verbs atlas_authorize, atlas_commit_effect and atlas_verify_audit.

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?

Gives a clear operational boundary: approval can only be given by a human through the atlas-mcp CLI, never through this server, which tells the agent not to attempt to resolve a pending_approval state here. It does not, however, state when to call this (e.g. poll after submitting a request) or name a sibling as the alternative for the approve action.

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