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

With no annotations provided, the description carries full behavioral burden. It discloses that the tool reads server-delivered HTML only, refuses JS-rendered and authenticated pages, follows pagination, deduplicates, and reports field presence frequency. It also states the pricing model. These are non-obvious behaviors beyond the schema, making the description transparent.

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 three sentences, front-loaded with the core action, then enumerates behaviors, then states the HTML limitation and pricing. Every sentence adds information; there is no filler or repetition. The structure is efficient and scannable.

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?

For a complex tool (pagination, dedupe, refusal conditions, reporting), the description covers the essential operational aspects: what it does, what it refuses, pricing, and output behavior (field presence report). It does not specify the exact output schema, but that is not required in the absence of an output schema. It also does not mention rate limits or error handling, but these are minor gaps given the clarity of the rest.

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?

The input schema already covers 100% of parameters with descriptions, so the baseline is 3. The description adds value by clarifying that 'fields' are extracted per record and that the tool reports how often each field was present, giving semantic meaning to the fields parameter. It also ties 'quantity' to the per-record pricing model, which supplements the schema's numeric constraints.

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 pair ('Extract structured records from a public web page') and enumerates concrete behaviors (finds repeating block, pulls named fields, follows pagination, removes duplicates, reports field presence). It clearly distinguishes itself from the data-intelligence siblings (hsh-b2b-contact, hsh-company-intelligence) by focusing on raw HTML scraping and explicitly scoping to public pages.

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 explicit conditions of use: it works on static public HTML and explicitly refuses dynamic (JS-rendered) or login-protected pages before charging. It also states pricing per record, which helps an agent decide based on cost. It does not name alternative tools, but the refusal conditions and 'public web page' scoping are strong usage guidance.

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