Skip to main content
Glama
Sign In

Boundra — Payment Approval Gateway for AI Agents

by io.boundra
OverviewDiscussionsAdmin

release_evaluation

Idempotent

Release a reserved ALLOW budget when the payment failed or was abandoned. Requires the evaluation_id and reservation_token returned by evaluate_payment.

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": {
      "evaluation_id": "<evaluation_id>",
      "reservation_token": "<reservation_token>"
    },
    "name": "release_evaluation"
  }
}

Input Schema

NameRequiredDescriptionDefault
evaluation_idYesEvaluation identifier returned by an ALLOW verdict
reservation_tokenYesPrivate reservation capability returned with the evaluation; never log or publish it

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / evaluation_id / description
      Added value: +"Evaluation identifier returned by an ALLOW verdict"
    • addedInput schema / properties / reservation_token / description
      Added value: +"Private reservation capability returned with the evaluation; never log or publish it"
  2. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, idempotent, non-destructive mutation, which is consistent with 'release'. The description adds the dependency on a prior evaluate_payment call and its returned capability token, but says nothing about repeat-release behavior, expiry, or what happens if the reservation is already gone — behavior the annotations only partially cover.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, zero filler, with the action and its precondition front-loaded. Every clause carries information an agent needs before calling.

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?

An output schema exists, so return values need not be explained, and the two-parameter flow from evaluate_payment to release is clear. Minor gap: nothing about timing or whether the release must occur before some reservation window closes.

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 both parameters are documented there, including that the token is private. The description restates provenance ('returned by evaluate_payment') without adding format, constraint, or failure-mode detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource ('Release a reserved ALLOW budget') plus the triggering condition ('when the payment failed or was abandoned'). That condition implicitly separates it from the settlement path, but no sibling tool is named, so an agent must still infer that settle_evaluation is the alternative.

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 when-to-use rule: the payment failed or was abandoned. No explicit when-not guidance or named alternative, but the failure/abandonment condition is a usable selection criterion on its own.

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

All Boundra — Payment Approval Gateway for AI Agents toolsInspect
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