Skip to main content
Glama
tremendous-mcp

tremendous-mcp

by Bryan21B

Review rewards before sending

review_rewards
Read-only

Prepare a reward batch for review without sending: validate recipients, amounts, campaign/products, and funding source, then return a draft ID to send.

Instructions

Prepare a batch of rewards WITHOUT sending anything. Checks the recipients, amounts, campaign/products and funding source, and shows an editable review form with a Send button. Use this before send_rewards. Returns a draft_id to pass to send_rewards.

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": {
      "recipients": "<recipients>"
    },
    "name": "review_rewards"
  }
}

Input Schema

NameRequiredDescriptionDefault
messageNo
languageNo
productsNoProduct IDs the recipient can choose from. Overrides the campaign's products.
deliver_atNoYYYY-MM-DD, within the next year. Delivered at 12pm org time.
recipientsYes
campaign_idNoTremendous campaign ID. Either campaign_id or products is required.
sender_nameNo
subject_lineNo
currency_codeNoISO 4217, e.g. EUR. Defaults to the organization currency.
delivery_methodNoEMAIL
funding_source_idNoFunding source ID, or BALANCE / INVOICE / INVOICE_THEN_BALANCE.BALANCE

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint; the description adds the substantive behavior an agent needs: it validates recipients, amounts, campaign/products and funding source, surfaces an editable review form with a Send button, and returns a draft_id for the follow-up call. The one nuance left unstated is that a draft_id is persisted state, which sits slightly at odds with the readOnly framing, though the 'WITHOUT sending anything' clause makes the intent clear.

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?

Four short sentences with the no-send constraint front-loaded and the draft_id handoff placed last. The 'editable review form with a Send button' detail is slightly UI-oriented for an agent audience but does explain why the call terminates in a handoff.

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 an 11-parameter, no-output-schema tool, the description covers the essential contract: no side effects on sending, what gets validated, and what value flows into send_rewards. It does not say what a failed validation returns or whether a draft can be reused, which are the remaining gaps.

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 45%, so several parameters (message, language, sender_name, subject_line, delivery_method) carry little or no documentation anywhere. The description names the concepts being validated (recipients, amounts, campaign/products, funding source) and hints that message/subject fields are optional via the review form, but it adds no format or constraint detail 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?

The description opens with a specific verb and resource ('Prepare a batch of rewards') and immediately caps the scope with 'WITHOUT sending anything'. That single clause separates it cleanly from send_rewards without the agent needing to open either schema.

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?

'Use this before send_rewards' gives an explicit sequencing rule and names the alternative, and 'WITHOUT sending anything' implies the counterpart case. What's missing is a stated exception, e.g. when it's acceptable to skip review and call send_rewards directly.

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