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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint true, and destructiveHint false. The description adds significant behavioral context: it probes multiple LLMs, defaults to Workers AI, requires BYO key for Anthropic, and returns per-model structured data. It also mentions that Anthropic calls are billed directly by Anthropic, adding transparency about costs. No contradiction 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 extremely concise: two sentences that convey the core action, options, return structure, and use cases. Every sentence earns its place, with no fluff. The key information is front-loaded.

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 parameters, no output schema, annotations present), the description covers all essential behavioral aspects: default model, optional Anthropic probing, return structure (per-model fields + combined view), and appropriate use cases. The lack of an output schema is compensated by listing the fields. No gaps remain.

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 value by explaining the _apiKey parameter as 'passed straight through to api.anthropic.com' and highlighting the default model. However, it does not elaborate on the 'models' parameter beyond the schema, missing an opportunity to clarify the exact model versions or capabilities. Still, it adds meaningful context.

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 action ('Probe one or more LLMs'), the resource ('business/brand/product/topic'), and the output ('score visibility 0-100 per model'). It is specific and distinctive from sibling tools like 'scan_competitor_ai_presence' which focuses on scanning competitors rather than general entity visibility.

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 provides clear usage scenarios ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains when to use the default model vs Anthropic. However, it does not explicitly exclude alternatives or compare against sibling tools like 'scan_competitor_ai_presence', missing a 'when not to use' clause for a perfect score.

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