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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior, so the safety profile is covered. The description adds value by disclosing that the tool calls ai_visibility_check internally, returns a ranked list, and includes score, confidence, and signal density per entity. This is meaningful context beyond annotations, though it doesn't describe error 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?

The description is two sentences, front-loaded with the core action ('Compare AI visibility across multiple entities side-by-side'). Every sentence earns its place: the first states purpose, the second explains mechanism and return value. No fluff 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?

Given there is no output schema, the description compensates by explicitly listing return fields (ranked list with score, confidence, signal density). Combined with strong annotations and full parameter coverage, the context is largely complete. Minor gaps: it doesn't mention model limitations or potential errors, but these are less critical for a read-only, idempotent tool.

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 has 100% coverage with descriptions for every parameter (entities, models, _apiKey, context). The description's mention of 'your brand + N competitors' and 'shared context' merely restates what the schema already provides. With such high schema coverage, the description adds minimal new parameter-specific meaning, so the baseline score of 3 is appropriate.

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 verb ('Compare'), resource ('AI visibility across multiple entities'), and scope ('side-by-side'). It also specifies the mechanism ('Probes each entity with ai_visibility_check, ranks by score') and differentiates from the sibling ai_visibility_check by focusing on multi-entity comparison. The example ('does Claude know about us as well as our competitors?') further clarifies intent.

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 explicitly frames when to use: 'Useful for competitive AI-marketing audits' and provides a concrete query scenario. It implies that this tool is for comparing multiple entities, which indirectly distinguishes it from the single-entity ai_visibility_check sibling. However, it does not explicitly state 'use ai_visibility_check for a single entity' or list alternative tools, so it misses explicit exclusions.

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