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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, so the safety profile is covered. The description adds valuable behavior beyond that: the default model (Llama-3.3-70b), the free tier, the cost implication of passing _apiKey ("you pay Anthropic directly"), and the external call to api.anthropic.com. This enriches the annotations without contradicting them.

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 main action is front-loaded in the first sentence, and each subsequent sentence earns its place: cost/model behavior, return format, and use cases. It is slightly dense — the cost point and return format could be tightened — but there is no fluff or redundancy beyond a minor BYO-key/pay overlap.

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 present, the description correctly fills the gap by specifying the return shape (per-model score, confidence, signals, raw_response + combined view). It also covers cost, defaults, and use cases. Minor gaps remain: the meaning/orientation of the 0-100 score (higher = better visibility?) and failure behavior when anthropic is requested without _apiKey are not explained.

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 the schema already documents all four parameters with examples and format hints. The description adds only marginal enrichment — the concrete default model identity (Llama-3.3-70b) and the free-vs-paid cost distinction for models/_apiKey. This is a solid baseline with slight bonus, but the schema carries the heavy lifting.

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 specific verbs and resources: "Probe one or more LLMs... and score visibility (0-100) per model." It names the subject (business/brand/product/topic), the action (probe + score), and the output shape, making it clearly distinguishable from Q&A siblings like ask_pipeworx and research tools like deep_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 final sentence gives concrete use cases ("AI-marketing audits, pre-launch brand checks, competitive monitoring"), and the second sentence provides operational guidance on model selection (default free model vs. BYO Anthropic key). However, it does not name alternative tools or state when not to use it, e.g., versus the sibling scan_competitor_ai_presence.

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