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

Annotations indicate read-only, idempotent, and open-world hints; description adds significant behavioral detail: probes multiple models, scores 0-100, returns per-model breakdown, requires Anthropic key for that model, and explains cost implications. No contradictions.

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 efficiently cover purpose, model options, and output structure with no redundant information. Front-loaded with key action and outcome.

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?

Despite no output schema, the description clearly indicates return format (per-model {score, confidence, signals, raw_response} + combined view). Parameters are fully described with schema and supplemented text. Use cases and warnings about API key are included, making it self-sufficient for an AI agent.

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%, but description adds value by explaining defaults (Workers AI Llama-3.3-70b free), that _apiKey is passed through to Anthropic, and that context helps disambiguate. This goes beyond schema 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 clearly states the tool probes LLMs to score brand visibility with a specific verb (Probe) and resource (LLMs). It distinguishes from siblings like scan_competitor_ai_presence by focusing on general AI visibility audits rather than competitor-specific scanning.

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 lists use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring) and explains default model vs. BYO key for Anthropic. It does not explicitly state when not to use or compare to alternatives, but context is clear.

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