Skip to main content
Glama

Approve or reject action-campaign proofs

review_submissions
Destructive

The owner's decision on proofs, free. approve PAYS the task's reward (points at once, or USDC from the funded pool via ProductClank's payout run) — show the user each proof (proof_url / screenshot_url, the member's profile_url) and get their decision first; never approve on your own judgment. reject reopens an exclusive task for others; that member can't redo it. Up to 20 decisions per call, each applied on its own.

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": {
      "campaign_id": "<campaign_id>",
      "decisions": "<decisions>"
    },
    "name": "review_submissions"
  }
}

Input Schema

NameRequiredDescriptionDefault
decisionsYes
campaign_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the destructiveHint=true and idempotentHint=false annotations, the description discloses the economically significant behavior: approve pays out the task reward, either points immediately or USDC from a funded pool, and reject reopens an exclusive task with no redo for that member. It also warns that up to 20 decisions are applied individually, signaling that partial application is possible.

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?

It is a single dense paragraph but front-loaded with the core statement and then organized by branch (approve, then reject) plus the batch rule. Almost every clause carries operational weight; 'free' and the proof-field references are mildly ambiguous but not wasteful.

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 destructive, non-idempotent mutation with no output schema, this covers the important ground: payout mechanics, irreversible rejection, batching, and the human-in-the-loop requirement. It does not state what the call returns per decision or how partial failures are reported, which an agent handling 20 mixed decisions would want.

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

Parameters4/5

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

With 0% schema description coverage, the description carries the load and does explain the crux: what 'approve' and 'reject' actually cause, which the enum alone does not convey. It also references proof_url, screenshot_url and profile_url as things to surface to the user, though those are not inputs to this schema. campaign_id and submission_id remain semantically unexplained beyond their names.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names specific verbs and the resource: it is the owner's approve/reject decision on proofs, and it spells out the consequence of each branch (approve pays the reward, reject reopens the task). It is not differentiated from the sibling review_posts, so an agent cannot tell from the text alone which review tool applies to which resource, keeping it out of 5-point territory.

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?

Clear operating context is given: show the user each proof and get their decision first, and 'never approve on your own judgment' is an explicit when-not rule. The batch limit of 20 decisions per call with each applied independently is also stated. What is missing is any reference to alternative tools (e.g. review_posts) that the agent should consider instead.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.