Skip to main content
Glama
thenavidm
by thenavidm

Create commission

create_commission
Destructive

Create custom, lead, or sale commissions for a partner, including clawbacks via negative amounts. Await asynchronous processing via GET /commissions or webhooks.

Instructions

Create one or more commissions (custom, lead or sale) for a partner. Custom commissions accept a negative amount to create a clawback. Commission creation is processed asynchronously – use the GET /commissions endpoint or webhooks to be notified when the commission is created.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
accountNoExact configured private workspace profile label; not a tenant or provider account ID.
confirmNoMust be true for the requested mutation or exclusive private output file.
payloadNoComplete native JSON body; do not mix with body flags or payload_file. Arrays use repeated JSON object flags or a whole native array in a private file.
payload_fileNoAbsolute regular non-symlink JSON body file, at most 1 MiB. Cannot mix with payload/body flags.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare the write/destructive/non-idempotent profile, so the bar is lower, yet the description adds a genuinely important behavioral trait: creation is asynchronous and requires polling or webhooks. It also flags the clawback behavior (negative amount). It does not mention the `confirm` mutation gate, which would have been useful context.

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?

Three tight sentences: creation scope first, key edge case (clawback) second, asynchronous follow-up last. Every sentence earns its place with no padding.

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 three-branch, nested payload schema with no output schema, the description adequately orients the agent (types, clawback rule, async result handling). It stops short of explaining what each branch requires or the confirm/account prerequisites, but the schema covers those, so the gap is minor.

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% and nested branches are fully documented inline, so the schema carries parameter meaning. The description only echoes the negative-`amount`/clawback rule already in the schema and lists the three type values, adding no new syntax or format detail. Baseline 3 applies.

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 ('Create ... commissions') and enumerates the three supported commission types (custom, lead, sale), which an agent can map to the oneOf branches. This clearly distinguishes it from the create-adjacent siblings list_commissions, update_commission, and bulk_update_commissions.

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?

Provides post-creation guidance (async processing; poll GET /commissions or use webhooks) but never states when to reach for this tool versus the semantically overlapping track_lead/track_sale or update_commission. Usage is implied by the verb/resource rather than explicit.

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