meta_ads_analysis_compare_ads

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

With no annotations, the description carries the safety disclosure burden by clearly stating 'Read-only.' It also explains behavioral context ('same targeting, same budget') and describes the output structure, adding meaningful transparency beyond the absent 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?

Three sentences, front-loaded with the main purpose, followed by output details and usage guidance. No redundancy or filler—every sentence contributes valuable 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?

Since there is no output schema, the description compensates by detailing the return fields (impressions, spend, conversions, CPA, CTR, relative-score, verdict). Combined with rich schema descriptions and an explicit read-only statement, the description is sufficient for correct tool selection and invocation.

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 schema already provides 100% coverage with detailed descriptions for all three parameters. The tool description adds no new parameter-specific semantics, only restating the ad_set_id scope that is already in 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 clearly states it 'Runs an A/B-style comparison of ads inside a single ad set,' specifying the exact verb and resource scope. It distinguishes itself from sibling analysis tools by focusing on intra-ad-set comparison and producing verdicts like winner/laggard.

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?

It gives explicit use case: 'Use this to decide which creatives to pause' and pairs with meta_ads_ads_pause for action. However, it does not explicitly name an alternative analysis tool for cross-ad-set comparisons, though the scope restriction ('inside a single ad set') implies a boundary.

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