Skip to main content
Glama
Heliyos MCP server

Heliyos MCP server

Official
by heliyos-ai

Approve or reject a review

heliyos_reviews_decide
Destructive

Decides one pending review by approving the worker's proposed action or rejecting it with feedback. Approving executes the action on the user's behalf, so review and confirm first.

Instructions

Decides one pending review. Approving does the thing the worker proposed: the email is sent, the deal or label is changed, the meeting is booked, or the paused run continues with its action; rejecting discards it and tells the worker why (feedback). A review is decided once; a second call fails. Approving acts on the user's behalf and cannot be undone: read it with heliyos_reviews_get and confirm with the user first. For a deal_update you may pass the fields as the user edited them in data; for a paused tool call, edited arguments in args. Returns structuredContent {review_id, decision, status, run_notified}.

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": {
      "review_id": "<review_id>",
      "decision": "<decision>"
    },
    "name": "heliyos_reviews_decide"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsNoA paused tool call and approved only: the tool's arguments as the user edited them (see proposal in heliyos_reviews_get).
dataNodeal_update and approved only: the deal's fields as the user confirmed or edited them (field key to value).
commentNoA note kept on the review.
decisionYesapproved or rejected.
feedbackNoWhat to tell the worker, for example why it was rejected or what to change.
review_idYesreview_id: a 24-character hex id.

Output Schema

NameRequiredDescriptionDefault
reviewNo
statusYes
decisionYes
review_idYes
run_notifiedYesfalse: the change was applied but the paused run could not be told; it will be picked up later.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds substantive context beyond them: the concrete side effects of approval, the explicit irreversibility warning, the user-consent requirement, and the fact that a second call fails. The only thing not covered is failure modes other than double-decision (e.g., stale or already-executed runs).

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 is front-loaded in the first clause, followed by consequences, constraints, and parameter notes in a sensible order. The four-item enumeration of approve outcomes is slightly long but each item conveys a distinct side effect, so little is wasted.

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?

For a destructive, non-idempotent decision tool with a rich schema and an output schema, the description covers purpose, side effects, irreversibility, consent workflow, and the conditional parameter split. Nothing an agent needs in order to call it correctly 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 description coverage is 100%, so all six params are already documented, and the description's notes on `data` and `args` largely restate the schema's own "deal_update and approved only" / "paused tool call and approved only" wording. It adds modest value by tying `feedback` to the reject flow, but does not go meaningfully beyond the schema.

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 ("Decides one pending review") and immediately enumerates what the decision does across the possible proposal types (email sent, deal/label changed, meeting booked, paused run continued). This distinguishes it cleanly from the read-only sibling heliyos_reviews_get, which it names explicitly.

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?

Gives explicit preconditions and an ordering: read the review with heliyos_reviews_get and confirm with the user before approving. It also states the one-shot constraint ("A review is decided once; a second call fails") and routes the two conditional params to the right proposal type, so an agent knows both when to call and how to sequence it.

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

Deploy Server

Other Tools