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

Beyond annotations (readOnlyHint, idempotentHint, etc.), the description adds valuable context: the free default model, the cost implication of Anthropic ('you pay Anthropic directly'), and the return structure (score, confidence, signals, raw_response). This enhances understanding of the tool's behavior without repeating annotation info.

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 a single well-structured paragraph that front-loads the primary action and output, then efficiently covers parameters, return format, and use cases. Every sentence adds value, with no redundancy or fluff.

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?

For a tool with 4 parameters, no output schema, but annotations providing safety context, the description fully compensates: it details return structure (per-model and combined view), explains when to use each parameter, and lists representative use cases. It leaves no obvious gaps in understanding.

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?

With 100% schema coverage, baseline is 3. The description adds meaningful context: it explains the default model behavior, the optional _apiKey's pass-through nature, and the purpose of the context parameter. This goes beyond the schema's basic descriptions, providing richer semantic understanding.

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' and identifies the resource as 'one or more LLMs for what they know about a business / brand / product / topic' and the output as a 'visibility score (0-100) per model'. It distinguishes itself from siblings like 'scan_competitor_ai_presence' by focusing on scoring visibility across multiple models, as evidenced by the example use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.'

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 explicitly states the default model and when to use an API key for Anthropic, and lists concrete use cases (e.g., AI-marketing audits). However, it does not explicitly state when NOT to use this tool or provide direct alternatives, though the context of sibling tools implies competition. This is still clear guidance for most scenarios.

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