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

The annotations already declare readOnly, openWorld, idempotent, and non-destructive, lowering the bar for description transparency. The description adds valuable behavior beyond that: it says the tool 'Probes each entity ... with ai_visibility_check, ranks by score', and discloses the output fields ('ranked list with score, confidence, signal density per entity'). This is meaningful context that annotations alone don't provide.

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 extremely concise: two sentences (plus a quoted example) accomplish everything. The action is front-loaded, and each sentence adds critical information—the probe method, ranking behavior, return format, and a concrete use case—without any fluff or repetition of schema details.

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?

With no output schema, the description compensates by clearly stating the return format ('ranked list with score, confidence, signal density per entity'). It also explains the process (probes each entity with ai_visibility_check, ranks by score) and gives a realistic scenario. Minor gaps remain, such as how results are aggregated when multiple models are specified, but for a comparison tool of this complexity the description is sufficiently complete.

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%—every parameter (entities, models, _apiKey, context) has a thorough description, including the nuance that the first entity is treated as the subject. The tool description adds no additional parameter semantics beyond what the schema already covers; it merely mentions 'your brand + N competitors', which is already implicit in the entities parameter description. Thus the baseline of 3 applies.

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 the specific action 'Compare AI visibility across multiple entities side-by-side', immediately distinguishing this from single-entity tools like ai_visibility_check. It further clarifies the scope by mentioning 'your brand + N competitors' and naming the exact probing mechanism (ai_visibility_check), making the tool's role completely unambiguous.

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?

Explicitly frames the tool for 'competitive AI-marketing audits' with a concrete example question ('does Claude know about us as well as our competitors?'), giving clear guidance on when to use it. It implies that for a single entity one would use ai_visibility_check instead, but it doesn't explicitly state this exclusion or name other alternative tools, so it falls short of a full when-not-to-use specification.

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