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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the return structure in detail and explicitly discloses the null case ('Returns null if no attribution data exists for the campaign'), which is a valuable behavioral trait. It also hints at data freshness with provisional and finalized counts, adding transparency. However, it does not explicitly state whether the operation is read-only or safe, though 'get' implies it. This is a minor gap given the otherwise thorough description.

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 sections: a one-line purpose, 'WHEN TO USE' bullet points, and a structured 'RETURNS' list. It front-loads the purpose and uses concise, scannable formatting. Every section earns its place, providing necessary details (especially return fields) without unnecessary fluff.

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 the lack of an output schema and annotations, the description provides complete context for using the tool. It fully explains the return object's structure (reach, footfall, cost, quality, dataFreshness) and the null-case behavior. It also covers usage scenarios, making the tool self-sufficient for an agent to understand its purpose, invocation, and interpretation of results.

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 schema covers the single parameter campaign_id with a clear description ('Campaign identifier (UUID or string ID from create_campaign)'). Since schema coverage is 100%, the baseline is 3. The tool description does not add extra semantics about the parameter beyond what the schema provides, though it does contextualize that this is for a DOOH campaign. Overall, the description adds minimal value over the schema, so a baseline score 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's purpose: 'Get comprehensive attribution summary for a DOOH campaign.' It uses a specific verb (Get) and resource (attribution summary for a DOOH campaign), which distinguishes it from sibling tools like get_attribution_timeseries (time-series data) and get_creative_attribution (creative-level data). The detailed RETURNS section further reinforces the tool's specific output scope.

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 provides a clear 'WHEN TO USE' section with three practical scenarios: measuring campaign effectiveness, getting a high-level view, and checking statistical significance. This gives strong contextual guidance for when to invoke the tool. However, it does not explicitly state when NOT to use it or mention alternative tools for specific cases (e.g., get_attribution_timeseries for time-series data), so it lacks exclusions/alternatives.

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