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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds substantial context beyond them: per-page metering against the data_api/api_calls tariff, NULL preservation, cursor-based continuation, and the provenance/identity fields. It meaningfully extends the safety profile with billing and continuation semantics.

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?

Dense but every sentence carries information: page scoping, NULL behavior, date constraints, polling, identity/provenance fields, and billing. Front-loaded with the core action, no filler.

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?

With no output schema, the description helpfully names return-relevant fields (canonical_key, reward_revision_id, build_stamp) and explains billing and paging, covering what an agent needs. The main missing piece is guidance on when this tool is preferable to sibling read tools.

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 the schema already documents all six parameters in detail (date patterns, limit max, cursor semantics, idempotency key). The description largely restates date format and cursor polling, adding little parameter-level meaning beyond the schema.

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?

States a specific verb ('Read') and resource ('latest measured native play states'), with clear scope ('metered page'). It is distinguishable from siblings, though the jargon 'measured native play states' is idiosyncratic and doesn't obviously map to 'creative rewards' in the tool name.

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 operational guidance ('Poll with the returned cursor', date format and 31-day cap) and mentions that canonical_key plus reward_revision_id identify logical changes. However, it never states when to use this tool versus alternatives like get_creative_attention or get_creative_experiment, so selection guidance is only implied.

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