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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses that passing an _apiKey triggers external calls to Anthropic, with the user paying directly. This is a meaningful behavioral and cost disclosure. It could add more details about rate limits or data handling, but the added context justifies above-baseline scoring.

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 four sentences and front-loaded with the core purpose. Each sentence earns its place: purpose, model options, return format, and use cases. It is slightly longer than strictly necessary, but every added detail is useful and there is no 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?

For a tool with no output schema, the description adequately explains the return structure (per-model object with score, confidence, signals, raw_response, plus a combined view). It also covers model selection, cost, and use cases. It could mention error or edge cases, but overall it is complete enough for an agent to invoke correctly.

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 already 100%, which sets a baseline of 3. The description adds value by explaining the default model choice, the meaning of _apiKey (BYO key and direct payment), and the purpose of the context parameter (disambiguation). This goes beyond the schema, nudging the score 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 clearly states the tool's function: it probes one or more LLMs for knowledge about an entity and scores visibility from 0-100 per model. The verb 'probe' and resource 'LLMs' are specific, and the outcome (visibility score) is unique. However, it does not explicitly distinguish this tool from siblings like scan_competitor_ai_presence, so it misses the top score.

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 gives clear context for when to use the tool: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It also explains model selection (default vs. Anthropic) and the cost implication. However, it does not mention exclusions or alternative tools, so it falls short of a 5.

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