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

Annotations already indicate safe, read-only, idempotent behavior. The description adds valuable context: it probes LLMs, returns a visibility score (0-100), per-model results, and mentions cost implications for Anthropic. This goes beyond annotations and fully informs the agent about behavior.

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 sentences with no redundancy. The main purpose is front-loaded, followed by key details (default model, Anthropic option, return structure, use cases). Every sentence is informative and earns its place.

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?

Despite lacking an output schema, the description explicitly states the return structure (per-model object with score, confidence, signals, raw_response plus combined view). All four parameters are described in the schema, and the description adds enough context for correct invocation. The tool's moderate complexity is fully covered.

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 good descriptions for each parameter. The description adds semantic value by clarifying the default model, explaining the optional _apiKey purpose, and providing example values for 'entity' and 'context'. This provides a baseline of 3, and the extra usage hints raise it to 4.

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 specific verbs ('Probe', 'score') and clearly identifies the resource (LLM visibility for a brand/product/topic). It distinguishes from siblings by specifying the use case: AI-marketing audits, pre-launch brand checks, competitive monitoring, which are not covered by other tools like 'search' or 'entity_profile'.

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?

Provides clear context for when to use (visibility audits) and explains the default model and the optional Anthropic probe with BYO key. While it doesn't explicitly list alternatives, the specificity of the use case implicitly guides selection. Minor improvement would be to mention when not to use (e.g., for general search or entity details).

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