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

The description discloses the evaluation approach (historical similarity and causal prediction), the output structure (ranked list sorted by predicted VAS with confidence levels), and includes a detailed returns section. It does not mention side effects or limitations, which is acceptable for a read-only prediction tool with no 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?

The description is well-structured with sections for overview, when to use, returns, and an example. It front-loads the core purpose, and while longer than a two-sentence description, every section adds necessary information.

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 fully compensates by detailing the return shape (rankings with creativeId, predictedVAS, confidence, rank; metadata; suggested_next_queries) and providing a concrete example. This gives the agent a complete picture of how to invoke and interpret the tool.

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 input schema already provides 100% coverage for both parameters. The description goes further by including a fully worked example that demonstrates the expected format for moment_description (e.g., 'gym venue, evening, 6 viewers') and creative_ids, adding practical meaning beyond the schema's basic field 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 first sentence 'Given a moment description, rank candidate creatives by predicted VAS performance' clearly states a specific action (rank) and resource (candidate creatives) tied to a prediction goal. It distinguishes from sibling tools like get_content_recommendations by focusing on ranking specific candidates for a given moment context.

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 'WHEN TO USE' section lists four concrete use cases: creative selection, comparing multiple creatives, rotation optimization, and pre-campaign selection. It provides clear context on when the tool is appropriate, though it does not explicitly name alternatives or cases where it should not be used.

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