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

Annotations already establish read-only, open-world, idempotent behavior. The description adds valuable behavioral context beyond these: it reveals the default model, the cost/auth implication of using Anthropic ('you pay Anthropic directly'), and the return structure (per-model {score, confidence, signals, raw_response} + combined view). This exceeds the baseline expected given annotations and fully discloses relevant side effects (no side effects, but cost is disclosed).

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. It packs essential details (default model, cost, return format, use cases) without redundancy. Every sentence contributes meaningful information, and the structure flows logically from what → how → when.

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?

The description is complete for a read-only analysis tool: it explains inputs, outputs (including per-model response structure), default behavior, optional key handling, and typical use cases. With no output schema present, the description adequately covers return values. Given the tool's moderate complexity (4 params, 1 required), this is sufficient for correct invocation.

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%, so each parameter already has a description. However, the description adds meaning by clarifying the default model ('Default model is Workers AI Llama-3.3-70b'), the conditional nature of `_apiKey` ('only needed if anthropic is in models'), and that the key is 'passed straight through' to Anthropic. These details go beyond the schema and help the agent understand parameter interdependencies.

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 opens with a specific verb ('Probe') and resource ('LLMs'), and clearly states the output ('score visibility (0-100) per model'). This unambiguously differentiates it from sibling tools like scan_competitor_ai_presence by focusing on per-model scoring across multiple LLMs rather than presence in a single source.

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 use-case context ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains the default vs. optional model (Workers AI free, Anthropic BYO key). It does not explicitly mention when not to use the tool or name alternative tools, but the described scenarios are sufficient for an agent to select it appropriately.

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