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

Annotations already indicate read-only, idempotent, open-world, and non-destructive behavior. The description adds that each entity is probed with ai_visibility_check, results are ranked, and the output includes score, confidence, and signal density. No contradictions with 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 three sentences long, each serving a purpose: first explains the core comparison and ranking, second gives use case example, third specifies output details. No wasted words.

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 has no output schema, the description adequately describes the ranked list (score, confidence, signal density). It mentions the dependency on ai_visibility_check. However, it could mention error handling or limits (2-8 entities), though the schema specifies that. Minor gap.

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 100%, but the description adds crucial context: first entity is treated as the 'subject' for narrative, the models parameter lists supported models and API key requirements, and the context parameter disambiguates common names. This goes 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 clearly states it compares AI visibility across entities, probes each with ai_visibility_check, ranks by score, and surfaces most/least recognized. It distinguishes from the sibling tool 'ai_visibility_check' which targets a single entity, and 'compare_entities' which is more general.

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 explicitly says 'Useful for competitive AI-marketing audits' and provides an example question ('does Claude know about us as well as our competitors?'). While it does not state when not to use, the context makes it clear it is for multi-entity comparison, differentiating it from single-probe tools.

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