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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful context beyond that: it names the free default model (Workers AI Llama-3.3-70b), reveals that passing _apiKey triggers external calls to Anthropic with direct cost to the user, and discloses the return structure. This is valuable behavioral transparency not captured in 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?

Three sentences, front-loaded with the main purpose, followed by a cost caveat and return format. No filler words, and every sentence earns its place. The structure is ideal for quick parsing by an AI agent.

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's mention of per-model {score, confidence, signals, raw_response} and a combined view is essential and complete. It also provides use cases and the cost/API-key note. It could mention error handling or the exact format of 'signals,' but overall it is sufficient for a relatively simple tool with one required parameter.

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 schema already covers all parameters with meaningful descriptions (100% coverage), so the baseline is 3. The description adds value by specifying the default model name (Workers AI Llama-3.3-70b) and clarifying the conditional nature of _apiKey (only needed with 'anthropic' in models). This goes beyond what the schema states.

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 uses a specific verb ('Probe'), identifies the resource ('one or more LLMs'), and the outcome ('score visibility 0-100 per model'). It clearly distinguishes from siblings like scan_competitor_ai_presence by focusing on LLM knowledge and scoring rather than web presence. The use-case list reinforces its unique role.

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 mentions when this tool is useful: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It provides clear context but does not explicitly name alternatives or state when not to use it. Since sibling tools like ask_pipeworx or deep_research could overlap, a more explicit exclusion would be stronger, but the intended use cases are well-stated.

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