Track Payment

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

Annotations only indicate it's not read-only and not destructive. The description goes far beyond: it discloses that repeated transactionId is rejected (not deduplicated), that a new payment records a goal completion, that isRenewal skips that, that isRefund marks a refund instead of adding a row, and how attribution works when no visitor matches. All these behaviors are critical for correct invocation and are not in annotations.

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?

Every sentence earns its place. The description front-loads the core purpose, then covers exclusions and behavioral nuances in a logical flow. It is comprehensive but not redundant, and the structure guides the agent from general use to specific edge cases.

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?

Given 12 parameters, side effects (goal recording, refunds), uniqueness constraints, and attribution logic, the description covers all essential aspects an agent needs to invoke correctly. It even notes the requirement for websiteId/domain with a workspace token. With an output schema present, it doesn't need to describe return values, and it doesn't.

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?

Although schema coverage is 100%, the description adds meaning beyond field names: it explains that amount=0 records a free_trial goal, that amount with isRefund represents the refund amount, that transactionId must be unique, that isRefund requires an existing transactionId, that visitorUid is strongly recommended, and how customerId/email are used for attribution. This significantly enriches parameter understanding.

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?

The description starts with a specific verb and resource: 'Record a payment'. It immediately states the effect (revenue appears in get_overview, get_timeseries, visitor profile) and explicitly contrasts with track_goal ('use track_goal for conversions without revenue') and with automatic provider tracking ('Skip it when the site's provider... is tracked automatically'). This clearly differentiates from sibling tools.

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?

Provides explicit conditions for use and non-use: when to skip (provider tracked automatically), when to use track_goal instead, and how to handle refunds via isRefund. It also specifies when a transactionId can be reused (only with isRefund). This is the highest level of guidance, leaving nothing to inference.

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