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

Annotations declare readOnlyHint=true and destructiveHint=false, so the safety profile is already covered. The description adds valuable behavioral context: the same people see both versions, the call combines forecast and movement, the free tier limits to 10 simulated people per version without a key, and the forecast's accuracy caveats (strong on headlines, weak on emails/texts/ads/web pages). This goes beyond annotations and helps the agent set expectations. It doesn't describe rate limits beyond the daily free allowance, but the key behavioral traits are disclosed.

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 dense but well-structured: it front-loads the core purpose and methodology, then lists outputs, then covers free tier/key requirements, and ends with accuracy caveats. Every sentence earns its place, though the accuracy caveats paragraph is long and could be trimmed without losing essential guidance. It is appropriately sized for a tool with this complexity.

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?

Given the tool's complexity (6 params, no output schema), the description is quite complete: it explains the comparison method, output fields, free tier limits, key requirements, and accuracy caveats. The only gaps are explicit rate limits for the daily free allowance and a clearer statement of when to use sibling tools (e.g., compare_urls for URLs). But for an agent deciding whether to call this tool, the essential context is present.

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 83%, so the schema already documents most parameters. The description adds meaning by explaining the comparison methodology (same people see both versions), the free tier limit (up to 10 simulated people per version without a key), and the output structure (call, reason, movement counts, objections, report link). It also clarifies the 'count' parameter's credit usage ('Uses count credits to recruit plus count for version B'). This adds value 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 ('compare'), a resource ('two versions of copy or an email'), and a clear outcome ('Mimiq's call on which to ship'). It also distinguishes itself from siblings by naming the comparison method (same simulated people see both versions) and the output (call, reason, movement counts, objections, report link). This is a clear, specific purpose that an agent can act on.

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 description explains when to use this tool: when comparing two versions of copy or email on the same simulated people. It also provides context about free A/B testing limits and key requirements. However, it does not explicitly name sibling alternatives or state when NOT to use this tool (e.g., when comparing URLs, use mimiq.compare_urls). The context is clear but exclusions are implicit.

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