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

With no annotations, the description carries the full burden. It discloses the side effect of creating or reusing DSP segments, the data pushed (MAID hashes), and possible status outcomes ('no_cohort', 'credentials_missing', 'empty_cohort'). It does not cover rate limits or authentication specifics, but the disclosed behavior is above average.

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 well-structured with clear paragraphs, a WHEN TO USE section, a RETURNS list, supported destinations, and an example. Every section adds value without redundancy; the front-loaded purpose sentence immediately communicates the tool's function.

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?

Despite having no output schema, the description explicitly lists all returned fields and their meaning, covers supported destinations, and provides a usage example. The tool has only two parameters, and the description fully covers its behavior, use cases, and outcomes, making it complete for an agent to select and invoke correctly.

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 input schema already provides full coverage with descriptions for both parameters, including an enum for destination with DSP names. The description adds an example invocation and clarifies destination aliases (e.g., 'ttd (The Trade Desk)'), but most semantic value is already in the schema, so a baseline of 3 is appropriate.

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 clearly states the tool exports an exposed audience cohort to a DSP for retargeting, specifying the exact mechanism (pushes MAID hashes) and supported destinations. It distinguishes itself from sibling tools like export_dataset by focusing on DSP cohort activation for retargeting.

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?

The description includes a dedicated 'WHEN TO USE' section with concrete scenarios (e.g., DOOH retargeting, pushing to TTD/DV360/Meta, measuring lift). It does not explicitly mention when not to use the tool or name alternative tools, but the provided use cases are clear and actionable.

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