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

Annotations already indicate readOnly, idempotent, openWorld hints, and description adds value by explaining cost implications (free default vs BYO key for Anthropic) and return structure (per-model score, confidence, signals, raw_response). No contradictions with annotations, and behavioral traits beyond what structured fields provide are 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 concise (4-5 sentences) and front-loaded with the core action and outputs. Every sentence adds distinct value: action, default model, optional API key, return format, and use cases. No redundant or filler content.

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 has 4 parameters, no output schema, but rich annotations, the description covers purpose, usage, parameter specifics, and return format. It is sufficiently complete for an AI agent to invoke correctly, though it could mention error handling or rate limits for API calls.

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?

All parameters have descriptions in schema (100% coverage), and the description elaborates on their roles, including default models, API key purpose, and disambiguation via context. For example, it specifies that 'models' can be 'workers-ai' (free) or 'anthropic' (requires key), adding clarity beyond the schema.

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?

Description clearly states the tool probes LLMs for knowledge about an entity and scores visibility (0-100). It identifies the action ('probe'), resource ('LLMs'), and output format. While it doesn't explicitly distinguish from similar siblings like 'scan_competitor_ai_presence', the use cases (AI-marketing audits, brand checks) provide enough context for differentiation.

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 explains default model usage and when to provide an API key for Anthropic, giving basic usage guidance. However, it lacks explicit instructions on when not to use this tool or comparisons to alternatives like 'scan_competitor_ai_presence'. The mention of 'AI-marketing audits' implies a context but is not definitive.

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