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

Beyond the readOnly/openWorld/idempotent annotations, the description adds material operational detail: default model and cost implications (BYO key, pay Anthropic directly), auth requirements for the optional provider, and the precise per-model return shape. This is exactly the kind of context annotations do not convey.

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 efficiently written in four sentences (~65 words), front-loading the core purpose and then layering model selection, cost, output format, and use cases. The tautological 'BYO key — you pay Anthropic directly' slightly repeats the earlier _apiKey mention, but overall every sentence adds meaningful information.

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 clearly explains return values ('per-model {score, confidence, signals, raw_response} + a combined view'), which is essential. It also covers model options, cost/auth behavior, and primary use cases. Combined with exhaustive parameter schema descriptions and safety annotations, nothing critical is missing for a read-only probing 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?

Schema description coverage is 100%, and each parameter already has a clear description (e.g., _apiKey says 'only needed if anthropic is in models. Passed straight through'). The description adds only a marginal cost note about paying Anthropic and repeats the default model, so it does not move beyond the schema-driven baseline of 3.

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 opening sentence is highly specific: 'Probe one or more LLMs for what they know... score visibility (0-100) per model,' clearly naming the verb, resource, and output. However, it does not explicitly differentiate this from overlapping sibling tools like scan_competitor_ai_presence or compare_entities, so it falls short of the top score.

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 gives concrete use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains model selection (free Workers AI default vs. Anthropic with API key). It does not provide explicit 'when not to use' guidance or name alternative tools, so it earns a 4 rather than a 5.

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