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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable context beyond these: the default free model, the BYO API key with direct pass-through to Anthropic, and the fact that the user pays for Anthropic calls. This informs the agent about external network calls and cost implications without contradicting the annotations.

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 function, then details of model selection and output structure, and ends with use cases. Every sentence earns its place with no fluff or repetition.

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?

Given there is no output schema, the description effectively covers the return format with 'per-model {score, confidence, signals, raw_response} + a combined view.' It also explains the two model options and the context parameter. The combined view could be described further, but overall it is sufficiently complete for a moderate-complexity read-only tool with strong annotations.

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 a baseline of 3 applies. The description adds meaningful semantics: the default model when no models array is provided, the requirement of _apiKey specifically for Anthropic, the 'passed straight through' behavior, and the purpose of context for disambiguation. This enriches the schema's dry parameter definitions.

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 verb ('Probe'), the resource ('one or more LLMs'), and the specific output ('score visibility (0-100) per model'). It distinguishes itself from siblings by positioning as a broad brand/product/topic visibility check rather than a competitor-specific scan, such as scan_competitor_ai_presence.

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 clear context for when to use it: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It does not explicitly name alternative tools or exclusions, but the use cases effectively guide the agent on appropriate scenarios, meeting the 'clear context, no exclusions' level.

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