Score ad

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

Annotations already convey read-only and non-destructive behavior, so the description doesn't need to restate that. It adds context on what the prediction covers (e.g., goal fit, retention) but doesn't disclose limitations like URL accessibility or auth requirements. This is adequate but not rich beyond annotations.

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 with zero fluff. The first sentence front-loads the core function and output, the second gives usage guidance. Every clause earns its place, making it easy for an agent to parse quickly.

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?

For a prediction tool with fully documented parameters and read-only annotations, the description covers the essential output (score, dimensions, strengths, fix) and usage timing. It doesn't discuss error handling or performance caveats, but these are minor given the tool's simplicity and annotation coverage.

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 descriptions cover all three parameters (url, kind, intent) at 100% coverage, so the baseline is 3. The description adds minimal extra meaning—only implicitly linking intent to goal-fit scoring via the per-dimension list. It doesn't provide syntax or format details 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?

The description states a specific verb ('prediction') and resource ('ad'), and details the output: overall score, per-dimension breakdown, strengths, and biggest fix. This clearly distinguishes it from sibling tools like plan_ad or render_ad, which focus on creation rather than evaluation.

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?

Explicitly says 'Use BEFORE spending on distribution, or to rank variants', giving clear context on when to invoke. While it doesn't name alternatives or provide exclusions, the timing guidance is actionable and sufficient for an agent to select this tool appropriately.

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