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

With no annotations, the description carries the full burden of behavioral disclosure. It adds meaningful context by distinguishing 'owner-verified' facts as ground truth and advising preference over scraped RAG answers. It also communicates that the tool returns categorized facts (pricing, limits, etc.). It does not mention freshness or behavior for unindexed domains, but the core safety/trust trait is covered well.

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, each with a distinct purpose: what the tool returns, the owner-verified nuance, and when to use it. There is minor overlap between 'use these in preference to scraped RAG answers' and 'rather than a natural-language synthesis,' but the description is well-structured and free of filler.

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 tool has no output schema, so the description must explain return shape and behavior. It covers fact categories, owner-verified distinction, and use cases, but does not specify the exact structure of the returned facts (e.g., fields, formatting) or behavior for domains not in the index. This leaves some ambiguity for a straightforward lookup tool, but it is generally adequate.

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 description coverage is 100%: the 'domain' parameter is described with an example and full-URL acceptance, and 'category' has an enum listing all values. The description's mention of pricing/limits/features/contact aligns with the category enum but adds no syntactic detail beyond the schema. Baseline 3 is appropriate because the schema already handles parameter semantics.

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+resource ('Return structured facts extracted from a website') and enumerates fact types (pricing, limits, features, contact info). It clearly differentiates from the sibling tool 'ask_site' by emphasizing 'structured data rather than a natural-language synthesis', and from 'get_site_capabilities' by focusing on facts about the site rather than capabilities.

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 explicitly states ideal use cases: 'price comparison across multiple sites, feature matrix lookups, or any task where you need structured data rather than a natural-language synthesis.' It also gives guidance on preferring 'owner-verified' facts for critical comparisons. It does not explicitly name alternative tools but the contrast with natural-language synthesis implies ask_site as the alternative.

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