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

The description uses the verb 'calibrates,' which implies modifying model parameters, but the annotations declare readOnlyHint=true. This is a direct contradiction. No further behavioral context (e.g., about idempotency or side effects) is added beyond the annotations, which are contradicted.

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 relatively concise at two sentences, but could be more structured. It front-loads the persona and action, then lists inputs and outputs. Every sentence adds value, but there is minor redundancy (e.g., 'programmatic sources' and 'programmatic channels').

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 complexity (6 parameters, including async) and the annotation contradiction, the description is incomplete. It does not address the async behavior parameter, the idempotency guarantee, or clarify that the operation is read-only despite using 'calibrates'. The output schema exists but is not described.

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%, so baseline is 3. The description broadly lists parameter types ('model parameters, date ranges, impression IDs') but does not add meaningful detail beyond the schema's individual parameter descriptions.

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 calibrates marketing mix models by ingesting OpenRTB impression data, identifies the target persona (ad_revenue_ops), and specifies inputs and outputs. This distinguishes it from sibling tools like retail_media_attribution_bridge through its focus on programmatic channels and MMM.

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 mentions it's useful for improving model accuracy with real-time bidding data, but does not explicitly state when not to use it or provide comparisons to alternatives among the many attribution-related sibling tools. Usage context is implied but lacks exclusions.

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