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

Annotations already declare read-only, open-world, idempotent, and non-destructive behavior. The description adds valuable context beyond annotations: the default model (Workers AI Llama-3.3-70b) is free, passing `_apiKey` incurs direct Anthropic costs, and it discloses the return structure. This goes beyond what annotations alone tell the agent.

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 purpose and output, followed by cost implications and use cases. Every sentence earns its place with no 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?

There is no output schema, but the description compensates by specifying the return format: per-model {score, confidence, signals, raw_response} plus a combined view. It also covers practical contexts and cost implications. While it lacks error-handling or rate-limit information, for a read-only probe the description is sufficiently complete.

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%, with each parameter (entity, models, _apiKey, context) documented in the schema. The description reinforces the default model and BYO key behavior but adds no new parameter-level detail beyond the schema. Baseline 3 is appropriate when the schema fully covers parameter semantics.

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' with a clear resource ('one or more LLMs') and a concrete output ('score visibility (0-100) per model'). It is not a tautology and clearly states what the tool does. However, it does not explicitly differentiate itself from sibling tools like scan_competitor_ai_presence, which may overlap in purpose, so it stops short of full sibling distinction.

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 concrete use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It also explains when to pass `_apiKey` for Anthropic probing and notes the free default model. However, it does not explicitly mention alternatives or when-not-to-use scenarios, which would earn a 5.

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