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

With no annotations, the description carries full burden. It discloses key behavioral details: the matching logic (purchase events to exposures with time-decay weighting), the computation of incremental ROAS and sales lift, and the edge case of returning null if no transaction data exists. It does not discuss authentication, rate limits, or explicit read-only guarantees, but given the 'Get' verb and return-focused text, this is sufficient.

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?

The description is divided into clear sections: purpose, WHEN TO USE, and RETURNS, with bulletized output groups. It's more detailed than necessary for a one-parameter tool but all sections add value, especially the RETURNS list which substitutes for the missing output schema. The metaphorical opener 'Closes the ROAS loop' adds minimal redundancy.

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?

The tool has no output schema, so the description compensates by enumerating all returned data groups (transactions, attribution, salesLift, timing) with field names, and explicitly states the null return condition. Combined with the single well-documented parameter and clear usage scenarios, the description is complete enough for an AI to correctly expect the response shape.

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?

The only parameter is campaign_id, which the schema already describes as 'Campaign identifier' with 100% coverage. The description does not add any additional meaning to this parameter, so it holds at the baseline for good schema coverage.

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 opens with a specific verb+resource: 'Get Return on Ad Spend (ROAS)'. It then elaborates with the mechanism (matches purchase events to DOOH exposures with time-decay weighting) and output scope (ROAS, iROAS, sales lift). This clearly distinguishes it from sibling attribution tools, though it doesn't name them 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?

A dedicated 'WHEN TO USE' section lists three concrete scenarios: measuring revenue attributable to DOOH, getting ROAS/iROAS, and sales lift between exposed/control groups. This provides clear context for when to invoke the tool, but it does not mention alternative sibling tools or exclusions.

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