Skip to main content
Glama

BRAINIAC Agent Network Float

Find commission leakage

agent-networks_commission-leakage

Compare caller-supplied transactions with dated agent agreements and commission payments. Expected commission follows the agreement in force on the transaction date: fixed, percent, tiered by cumulative count under that agreement, or capped. transaction_types limit a rule to named types; type-specific agreements beat general ones, then the latest effective_from wins. Payments that name a transaction apply there first. Remaining payments apply FIFO to unpaid expected amounts for that agent. unpaid is expected minus paid. overpaid is paid above expected, including leftover unallocated payments. exposure is unpaid plus overpaid inside each currency. No ledger is fetched or stored. Price $0.04 USDC. POST /api/v1/agent-networks/commission-leakage. Unpaid calls return 402 and do not run.

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": {
      "agents": "<agents>",
      "rules": "<rules>",
      "agreements": "<agreements>",
      "transactions": "<transactions>",
      "payments": "<payments>"
    },
    "name": "agent-networks_commission-leakage"
  }
}

Input Schema

NameRequiredDescriptionDefault
rulesYes
agentsYes
paymentsYes
agreementsYes
transactionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses cost ($0.04 USDC), the failure mode (unpaid calls return 402 and do not run), and that nothing is fetched or persisted. It also explains the core allocation semantics (rule precedence, payment matching, FIFO, currency-scoped exposure), which an agent needs to predict results.

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?

Content is front-loaded with purpose, then derivation rules, then cost and failure mode — every sentence carries a fact. The dense telegraphic style ('unpaid is expected minus paid') is efficient but slightly less readable than full sentences.

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 five-array, computation-heavy tool with no annotations and no output schema, the description covers purpose, precedence, allocation, result fields, cost, and error behavior. It stops short of describing the result grouping or ordering (per agent, per currency breakdown shape), which is the main remaining gap.

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?

Schema description coverage is 0%, so the description must compensate, and it does for the important parts: the four rule kinds (fixed, percent, tiered, capped), tiers being cumulative count, transaction_types restricting a rule, agreement precedence, and transaction_id-tagged payments. It leaves details like the meaning of rate_bps (basis points) and cap interaction unstated, so not a 5.

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 first sentence states a specific verb (Compare) and the three resources compared: caller-supplied transactions, dated agent agreements, commission payments. The leakage framing ('unpaid', 'overpaid', 'exposure') makes the goal concrete. It does not name sibling tools or explicitly contrast with settlement-reconciliation, so it falls just short of 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Caller-supplied' and 'No ledger is fetched or stored' make the precondition clear: the agent must pass all five datasets in the call. However, there is no explicit when-to-use versus when-not-to-use guidance, and no named alternative among the sibling tools (e.g. settlement-reconciliation) for the case where the agent has only aggregate data.

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.

Resources