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

Annotations declare the tool read-only, idempotent, and non-destructive. The description goes beyond by explaining the default model is free, that passing '_apiKey' triggers external Anthropic calls with user-paid costs, and the return structure includes per-model score, confidence, signals, and raw response. This provides valuable behavioral context not captured in annotations.

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 compact at three sentences, front-loads the core purpose, and includes no redundant information. It efficiently conveys the tool's function, models, and typical use cases.

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 description covers the tool's input, output structure, and typical applications. However, it omits potential error scenarios (e.g., invalid API key, model unavailability) and rate limits. Given the richness of schema descriptions and annotations, the description is nearly complete but could benefit from mentioning these edge cases.

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 all parameters described. The description adds meaning beyond the schema by explaining the default model rationale ('free'), that '_apiKey' is passed straight through to Anthropic, and that 'context' helps disambiguate. This enriches the schema 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 a given entity and scores visibility per model. It uses specific verbs ('probe', 'score') and resources ('LLMs', 'visibility (0-100) per model'), distinguishing it from siblings that focus on different tasks (e.g., 'scan_competitor_ai_presence' for competitors).

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 context for when the tool is useful ('AI-marketing audits, pre-launch brand checks, competitive monitoring'), but does not explicitly state when not to use it or compare it to sibling tools like 'scan_competitor_ai_presence'. The guidance around API key and models is clear, but lacks exclusions or alternatives.

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