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

Annotations already indicate readOnly/idempotent/non-destructive, and the description adds behavioral detail: it probes with ai_visibility_check, ranks by score, and returns score, confidence, and signal density. This goes beyond the annotation hints, though it does not mention potential multi-call cost or rate limits.

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 purpose, process, use case, and return summary. Every sentence carries distinct information with no filler or redundancy.

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?

Despite having no output schema, the description explains the return format (ranked list with score, confidence, signal density). It also gives a concrete use case and example, making it easy to understand when to invoke this tool. No critical gaps for a comparative read-only operation.

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 comprehensive descriptions for all parameters (100% coverage), including the first-entity-as-subject rule and model options. The tool description adds minimal new parameter meaning, so it appropriately relies on 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 the tool's function: 'Compare AI visibility across multiple entities side-by-side.' It specifies the resource (AI visibility) and the action (compare/probe/rank), and distinguishes itself from sibling ai_visibility_check by focusing on multiple entities and ranking them.

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?

Provides a specific use case ('competitive AI-marketing audits') and an illustrative example query. It implicitly differentiates from ai_visibility_check by saying it 'probes each entity...' and returns a ranked list, but does not explicitly state when not to use it or name alternative tools for single-entity checks.

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