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

Annotations already declare readOnly, idempotent, and non-destructive hints. The description adds value by specifying that records include per-model {score, confidence, signals, raw_response} plus a combined view, and disclosing that generating a Anthropic requires a BYO key. No behavioral contradictions.

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, each serving a clear purpose: what the tool does, default behavior, return format, and use cases. No irrelevant 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?

Given the absence of an output schema, the description adequately explains the return format and use cases. It covers all 4 parameters and key behavioral details. Minor omission: no mention of error handling or rate limits, but not critical for 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 the schema already documents all parameters. The description adds contextual use-case framing (e.g., 'entity' is for brand/product) but does not significantly expand beyond the schema descriptions. Baseline of 3 is appropriate.

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 an entity and scores visibility (0-100) per model. It uses specific verbs ('probe', 'score') and resource ('LLMs'), and distinct use cases like AI-marketing audits and brand checks. It differentiates from sibling tools like 'scan_competitor_ai_presence' by focusing on per-model scoring rather than broad scanning.

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 checks, competitive monitoring) and explains the default vs. key-gated model option. However, it does not explicitly mention alternatives or when to use sibling tools like 'scan_competitor_ai_presence', so it lacks explicit exclusions.

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