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

Annotations already declare readOnly and idempotent, but the description adds behavioral details: it probes each entity, ranks by score, and returns a ranked list with score, confidence, and signal density. This goes beyond the safety hints to explain what the tool actually does internally.

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 three sentences, each earning its place: first states purpose, second explains mechanism, third provides use case and output format. No redundant phrasing or fluff.

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 moderate complexity (4 params, no output schema), the description is complete: it covers the input semantics, the process, and the expected return format. Annotations cover safety, and the schema covers all parameters, so nothing critical is missing.

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 coverage is 100%, so the baseline is 3. The description adds extra meaning beyond the schema by explaining that the first entity in 'entities' is treated as the subject, and that using 'anthropic' in models requires the '_apiKey'. This helps the agent correctly assemble parameters.

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 opens with 'Compare AI visibility across multiple entities side-by-side', which is a specific verb+resource. It distinguishes from the sibling ai_visibility_check by emphasizing multi-entity comparison and ranking, and from compare_entities by focusing on AI visibility specifically.

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 provides a clear use case ('competitive AI-marketing audits') and an example query, implying when this is useful. It does not explicitly state when not to use it or name direct alternatives, but the mention of probing with ai_visibility_check suggests the single-entity alternative.

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