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

Annotations cover read-only and idempotent safety. The description adds valuable context that it probes each entity via ai_visibility_check, ranks by score, and returns per-entity metrics (score, confidence, signal density). No contradiction with annotations, though it doesn't discuss failure handling 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 tight sentences: main function, method (probes via ai_visibility_check), ranking, use case, and return fields. No fluff, front-loaded with the core action.

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?

For a composite tool with no output schema, the description sufficiently explains return structure (ranked list with score, confidence, signal density) and the multi-entity behavior. It lacks details on edge cases like partial probe failures or tie-breaking, but expectations are otherwise clear.

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 documentation covers 100% of parameters, so the description adds little beyond what the schema already states. The description's 'your brand + N competitors' indirectly reinforces the entities semantics already in the schema, but no new parameter-specific meaning is introduced.

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 compares AI visibility across multiple entities side-by-side, explicitly naming the underlying probe (ai_visibility_check) and the output (ranked list). This distinguishes it from single-entity tools like ai_visibility_check and generic comparison utilities.

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 example question ('does Claude know about us as well as our competitors?'). It also implies the alternative ai_visibility_check for single-entity checks, but does not explicitly state when not to use it or contrast with compare_entities.

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