ghl_affiliate_delete_commission

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the bar is lower, yet the description still earns credit by disclosing a non-obvious side effect (the associated payout is updated) plus the token type and OAuth scope required. It stops short of saying whether the deletion is reversible or what happens if a payout is already issued, which is the one gap for a destructive operation.

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

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

Front-loaded with the imperative and its most important side effect, followed by endpoint, auth and scope — a sensible order for a large API surface. The "Version header: v3; source: v3/affiliate-manager-v3.json" fragment is provenance metadata of marginal value to an agent and could be dropped.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter delete with no output schema and rich annotations, the description covers everything needed to invoke it correctly: the resource identity, the cascading payout update, the endpoint shape, the required token type and the write scope.

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

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

Schema description coverage is 100% with only two string parameters, so the schema does the work and the baseline 3 applies. The endpoint template in the description does add a small amount of meaning by confirming locationId and commissionId are path segments, but no format or sourcing guidance beyond the schema's examples.

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

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

States a specific verb and resource ("Delete a commission") and adds a meaningful scope detail that a bare delete would lack: it also updates the associated payout. That side effect arguably differentiates it from sibling mutations like ghl_affiliate_deny_commission or ghl_affiliate_update_commission_status, though it never names a sibling explicitly.

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

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

Usage is only implied — an agent can infer "call this to remove a commission," but nothing tells it when to delete versus deny or change status, nor what preconditions must hold (e.g., payout not yet paid). The prerequisite it does state (Sub-Account token, affiliate-manager.write scope) is useful but auth-oriented rather than a selection rule.

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