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

Annotations already mark the tool as readOnly, openWorld, idempotent, and non-destructive, so the bar is lower. The description adds valuable behavioral context: the default free model, that using Anthropic requires a BYO key with direct payment to Anthropic, and the return structure (per-model score, confidence, signals, raw_response + combined view). This goes beyond the structured annotations and helps set expectations about cost and output.

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?

Three sentences total: the first states the core function and output, the second covers the default and optional API key with cost implications, and the third lists use cases. No filler, every sentence adds distinct value, and the most critical information is front-loaded.

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?

Given strong annotations (readOnly, idempotent, openWorld, non-destructive), 100% schema coverage, and no output schema, the description supplies the needed return format (per-model fields + combined view) and practical context (cost, defaults, use cases). This is sufficient for an agent to select and invoke the tool correctly without ambiguity.

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 covers 100% of parameters, so baseline is 3. The description adds meaningful semantics beyond the schema by explaining the default model (Workers AI Llama-3.3-70b free), that models can be omitted to use only the default, and that _apiKey is required only when probing Anthropic. It also clarifies the 'entity' parameter scope (brand, product, person, topic) which aligns with the schema's examples, adding enough to warrant a 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 opens with a specific action ('Probe one or more LLMs') and a clear resource ('what they know about a business / brand / product / topic'), then explains the scoring output (0-100 per model). This clearly distinguishes it from sibling tools like ask_pipeworx (which answer questions) and scan_competitor_ai_presence (which focuses on competitor scanning), making its unique function obvious.

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 concrete use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains the default model behavior plus the optional Anthropic key. While it does not explicitly list when not to use it or name alternative tools, the context is clear enough for an agent to choose this tool for visibility/awareness checks rather than other query tools.

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