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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false. The description adds meaningful context beyond these: the default model is free (Workers AI Llama-3.3-70b), passing _apiKey incurs direct costs to the user (BYO key), and the return structure is disclosed (per-model fields + combined view). This is substantive behavioral information not present in annotations, though it omits error behavior or rate limits.

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 three sentences, front-loaded with the core purpose, followed by specific invocation details and use cases. Every sentence contributes information without redundancy or fluff. It is efficiently structured and easy to scan.

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?

With no output schema, the description compensates by explicitly stating the per-model return fields ({score, confidence, signals, raw_response}) and the combined view. It covers key invocation aspects (default model, optional key, use cases) and the entity parameter's purpose. However, it leaves the meaning of 'signals' undefined and does not describe potential error conditions, which would round out completeness.

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 description coverage is 100%, so a baseline of 3 applies. The description adds extra value by explaining the default model (free Workers AI) and the cost implication for _apiKey ('you pay Anthropic directly'), which are not in the schema. It also gives example entity values, enriching the meaning of the 'entity' parameter.

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 states a specific verb ('probe') and resource ('one or more LLMs'), with a clear output (visibility score 0-100 per model). It also lists distinct use cases (AI-marketing audits, pre-launch brand checks, competitive monitoring), making it obvious what the tool does and how it differs from siblings like scan_competitor_ai_presence.

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 mentions when the tool is useful ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and provides practical invocation details (default model vs. optional Anthropic key). However, it does not explicitly state when to prefer an alternative tool or provide exclusions, so a clear context but no contrast with siblings.

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