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 valuable context beyond annotations: it specifies that calling Anthropic requires the user's own API key and that the user pays Anthropic directly for those calls. It also discloses the return structure ('per-model {score, confidence, signals, raw_response} + a combined view'). This gives the agent a clear picture of external side effects and outputs.

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, each earning its place: the first explains what the tool does, the second covers models and costs, and the third lists return format and use cases. It is front-loaded with the core purpose and avoids redundant fluff. No unnecessary details or repetition of the schema.

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 appropriately explains the return shape ('per-model {score, confidence, signals, raw_response} + a combined view'). It also covers the main parameters and their interplay (models list, _apiKey). The only minor gap is that 'signals' is not fully defined, and there is no detail on interpreting the score, but for a tool of this complexity the description is sufficient.

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 input schema has 100% description coverage, so every parameter is already documented. The description goes further by clarifying the value ranges for `models` ('workers-ai' free default, 'anthropic') and explaining why `_apiKey` is needed (only when Anthropic is included). It also gives concrete entity examples ('Pipeworx', 'OpenInvoice') that illustrate expected input, adding value beyond the schema's generic 'brand/business name'.

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's function: 'Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model.' This uses a specific verb ('probe') and names the resource (LLMs) and the outcome (visibility scores). It distinguishes itself from sibling tools like ask_pipeworx or deep_research by focusing on measuring model awareness rather than answering questions or conducting research.

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 context: default model is free ('Workers AI Llama-3.3-70b (free)'), when to supply an Anthropic key ('pass `_apiKey` to also probe Anthropic'), and example use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring'). It does not explicitly state when not to use it or name alternative tools, but the context is sufficient for an agent to decide appropriately.

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