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

Annotations already indicate read-only, idempotent, open-world, non-destructive behavior. The description adds valuable context: it probes multiple LLMs, requires an API key for Anthropic (with cost implications), and returns per-model details. This does not contradict any annotation and provides useful behavioral insight beyond the structured data.

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 (3-4 sentences) with no redundant information. It is front-loaded with the core action and output, then provides model details and use cases. Every sentence adds value, achieving high informational density without verbosity.

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 no output schema, the description explains the return format (per-model score, confidence, signals, raw_response, combined view) and use cases. It covers the tool's purpose adequately for a 4-parameter tool. Minor omissions like rate limits or error handling are acceptable given the idempotent/read-only annotations, but slightly less complete than ideal.

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% with each parameter described. The description reinforces the meaning of `_apiKey` (BYO key, pay directly) and context parameter (disambiguation). It adds a layer of understanding about default model and usage, which goes beyond the schema's basic descriptions.

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 probes LLMs for knowledge about an entity and scores visibility (0-100) per model. It specifies the verb 'probe', the resource 'LLMs', and the unique output format. This distinguishes it from sibling tools like 'scan_competitor_ai_presence' which have a different focus.

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 lists use cases: AI-marketing audits, pre-launch brand checks, competitive monitoring. It explains when to use (e.g., checking brand visibility) and provides context on default versus paid models. However, it does not explicitly mention when not to use or compare directly with similar sibling tools like 'scan_competitor_ai_presence', which slightly reduces the score.

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