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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds valuable context: the default model is free, passing `_apiKey` incurs direct Anthropic charges, and returns a per-model structure with score/confidence/signals/raw_response. This discloses cost implications and behavioral details beyond the annotations, though it does not cover potential rate limits or failure modes.

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 two sentences long, front-loaded with the core function, and contains no redundant phrases. It efficiently packs the model options, cost note, return format, and use cases without 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?

The tool has no output schema, but the description compensates by listing return fields ('per-model {score, confidence, signals, raw_response} + a combined view'). It also covers default behavior and optional API key usage. However, it does not explain what 'signals' contain or how the visibility score is computed, which could be important for an agent to trust the output. Overall, it is well-rounded for a read-only probing tool.

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 has 100% parameter coverage with detailed descriptions for each field. The description reinforces but adds little new meaning (e.g., names the exact default model 'Llama-3.3-70b' and repeats the BYO key cost note). Since schema coverage is high, a baseline of 3 is appropriate; the description contributes minimal additional semantics.

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 a specific action ('Probe one or more LLMs') and target ('business / brand / product / topic') with an output ('score visibility 0-100 per model'). It is specific and unambiguous, but it does not explicitly differentiate from sibling tools like 'scan_competitor_ai_presence', which may have overlapping functionality.

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 explicit use cases: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It also explains the default and optional configurations, giving clear context for when to use the tool. However, it does not mention when NOT to use it or compare it to alternatives like 'ask_pipeworx' or 'deep_research'.

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