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

Beyond the readOnly and idempotent annotations, the description reveals important behaviors: the default model (Workers AI Llama-3.3-70b) is free, calling Anthropic requires a BYO _apiKey and incurs direct costs to the user, and the return structure is disclosed ('Returns per-model {score, confidence, signals, raw_response} + a combined view'). This is genuine behavioral context that helps an agent anticipate side effects and requirements.

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 compact and front-loaded, with the primary action stated first. Each sentence carries unique information: purpose, default behavior/cost, return format, and use cases. No filler or redundant repetition of the schema or annotations.

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 the tool's moderate complexity (4 params, annotations, no output schema), the description covers all essential decision-making factors: what it does, what the return structure looks like, cost implications, and when to use it. The annotations already handle safety, so no further disclosure is necessary.

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?

The input schema already covers all four parameters with 100% description coverage, but the description adds value by specifying the default model, clarifying that omitting 'models' uses only the free workers-ai model, and noting that _apiKey is only needed when 'anthropic' is included. This supplements the schema's existing descriptions with operational details.

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 and resource: 'Probe one or more LLMs for what they know about a business / brand / product / topic and score visibility (0-100) per model.' This clearly states the tool's core function and distinguishes it from sibling tools like scan_competitor_ai_presence by focusing on knowledge scoring, not just presence detection.

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 cases: 'Useful for AI-marketing audits, pre-launch brand checks, competitive monitoring.' This gives agents context on when to deploy the tool, though it lacks explicit exclusions or alternatives (e.g., 'use this instead of scan_competitor_ai_presence when...').

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