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

Annotations already cover read-only, open-world, and idempotent behaviors. The description adds valuable context: it discloses that probing Anthropic requires a BYO key with direct cost to the user, and it reveals the return structure (per-model fields + combined view). It stops short of discussing potential failures or rate limits, but given the annotation coverage, this is solid.

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?

Two sentences deliver purpose, default behavior, cost model, return format, and use cases—zero wasted words. The main action is front-loaded, and every sentence carries information.

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 listing the exact return fields. It covers the default model, optional Anthropic probing, and practical use cases. While it doesn't explicitly mention the `context` parameter or error conditions, the schema covers those, and the overall picture is sufficient for an agent to select and invoke this tool.

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%, so baseline is 3. The description adds meaning beyond the schema by explaining the free default (Workers AI Llama) and the cost implication of `_apiKey` ('you pay Anthropic directly'), which helps agents decide whether to pass that parameter. It also ties the `entity` parameter to a broad concept ('business / brand / product / topic').

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 opens with a specific verb ('Probe') and a resource ('one or more LLMs') plus the core output ('score visibility (0-100) per model'). It clearly differentiates from sibling tools by focusing on LLM knowledge visibility for brands/topics, not asking questions or scanning competitors, and names concrete use cases.

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 contexts: 'AI-marketing audits, pre-launch brand checks, competitive monitoring.' It also notes the default model and the option to add Anthropic via `_apiKey`. However, it does not explicitly state when not to use this tool or mention alternatives among siblings (e.g., scan_competitor_ai_presence), so it misses the 'when-not/alternatives' level.

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