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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful non-annotation context: the exact price, the payment rail (x402 on Base, USDC), and crucially that failed calls aren't charged, which affects the agent's retry calculus.

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?

Two sentences, front-loaded with the operation, then billing terms. No filler and every clause carries information the agent needs.

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?

There is no output schema and no description of what a 'score' returns (numeric score, per-dimension breakdown, rationale), so the agent cannot anticipate the result shape. Billing and failure semantics are complete, but the return contract is a notable gap.

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 coverage is reported at 0% at the top level and the single parameter is a nested array of creative objects; the description says nothing about what constitutes a valid creative (script, hook, cta, platform). It only restates the maxItems of 10, which the schema already enforces.

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 and resource: 'Score up to 10 ad creatives', naming the operation and the batch limit. It doesn't explicitly distinguish itself from the sibling ad_creative_score (single-item), leaving the agent to infer the batch/single split from the name and 'up to 10'.

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?

'Up to 10 ad creatives' implies this is the bulk variant, but there is no explicit instruction on when to use this versus ad_creative_score, nor any guidance on cost trade-offs beyond the raw price. Usage is implied rather than stated.

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