Prubex

Check an approval request

approvals_get

Read-onlyIdempotent

Returns one approval and what became of it. pending: still waiting for a person. approved: a person approved it and Prubex is carrying it out; check again shortly. executed: Prubex did it (result.event_id for calendar actions; sends report no message id); for a feedback_suggest suggestion, it was emailed to Tech Mage. rejected: see decision_note. expired or cancelled: nothing happened. failed: approved, but it did not go; result.error and result.code say why. A person may edit a send before approving it, and decision_note then says so. Use it after a pending_approval result to tell the user what happened. Prubex performs approved actions itself: never resend one, and after failed try again only if the user asks. Example: { "approval_id": "apr_…" }.

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": {
      "approval_id": "<approval_id>"
    },
    "name": "approvals_get"
  }
}

Input Schema

Name	Required	Description	Default
`approval_id`	Yes	An approval id (`apr_…`) from a pending result.

Output Schema

Name	Required	Description	Default
`approval`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Annotations already declare readOnlyHint/idempotentHint, but the description goes well beyond them: it discloses that Prubex itself executes approved actions, that a human may edit a send before approval, and where failure detail lives (`result.error`, `result.code`). The "never resend one" warning is exactly the kind of side-effect caution an agent cannot infer from structured fields.

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?

Purpose and the when-to-use hook lead, with the status enumeration in the middle and the safety warnings near the end. It is dense but nearly every clause carries distinct operational meaning; only the terminal example feels slightly redundant given the schema.

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?

An output schema exists, so return-value explanation is not owed, yet the description still supplies the state-machine semantics (pending → approved → executed/failed) that an agent needs to narrate outcomes to a user. Nothing material for correct invocation or follow-up behaviour is missing.

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 coverage is 100% and the single parameter is fully documented there, so the baseline is 3. The description's only addition is the inline example `{ "approval_id": "apr_…" }` and phrasing the id as coming "from a pending result," which largely restates the schema text.

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?

Opens with a specific verb and resource ("Returns one approval") and immediately scopes it as a single-record lookup, which cleanly separates it from the sibling approvals_list. The status taxonomy that follows reinforces that this is a point-read of one approval's fate, not a listing.

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?

Explicitly says when to call it: "Use it after a `pending_approval` result to tell the user what happened," and adds operational guidance around retry ("never resend one, and after `failed` try again only if the user asks"). It does not name approvals_list as the alternative for enumerating approvals, so the sibling routing is implied rather than stated.

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

All Prubex 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?