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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: the default model is free, passing _apiKey invokes Anthropic and the user pays Anthropic directly, and the return shape is per-model {score, confidence, signals, raw_response} plus a combined view. 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, front-loaded with the core action and output, followed by default behavior and use cases. Every sentence adds unique information without redundancy or filler.

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?

The description covers the main function, default vs optional models, cost implication, return format, and use cases. With no output schema, it adequately describes what the agent can expect back. Minor gap: it does not explain what the 'signals' field contains or how the 0-100 score is derived, but this is not critical for invoking the 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?

All 4 parameters have schema descriptions (100% coverage), so the baseline is 3. The description adds extra semantics by explaining the default model selection ('Omit for just workers-ai'), the pass-through nature of _apiKey, and the disambiguation purpose of context. This goes beyond the schema's field descriptions.

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 a specific verb ('probe') and resource ('one or more LLMs'), defines the output score (0-100 per model), and includes concrete use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring), making the tool's purpose unmistakable. It distinguishes itself from similar sibling tools like scan_competitor_ai_presence by focusing on per-model visibility scoring.

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 lists explicit use cases ('Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring'), giving clear context for when to apply the tool. However, it does not mention when not to use it or point to alternatives like scan_competitor_ai_presence, so it falls short of explicit when/when-not guidance.

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