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

With readOnlyHint and openWorldHint already present, the description adds substantial behavioral context beyond annotations: de-duplication with counts, source distinction between model and pattern extraction, robots.txt compliance for URLs, per-call pricing, accepted payment networks, and the fact that failed calls are not charged.

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 tightly written sentences with no wasted words. It front-loads the output categories, then explains URL behavior, then mentions pricing, which is exactly the information an agent needs in a sensible order.

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?

An output schema exists, so return value structure is already covered. The description adds the key return semantics (entity categories and de-duplicated counts), input mode behavior, and pricing model, leaving no critical gap for an agent deciding whether and how to call the 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 description coverage is 100%, so both parameters are already documented. The description adds semantic meaning for the url parameter by explaining that the page's readable text is used and robots.txt is respected. It does not add extra detail for the text parameter beyond what the schema already provides.

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 names the specific resource (named entities) and enumerates the exact categories returned: people, organisations, places, dates, money amounts, e-mail addresses, URLs, and phone numbers. It also distinguishes the extraction sources (chat model vs. pattern-based), which helps separate it from generic extraction siblings.

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?

It establishes clear usage context: operate on either a text string or a page URL. It also states the special behavior for the URL mode (readable text is used and robots.txt is respected). It does not, however, compare itself against alternatives such as text_keywords or extract, or specify when not to use it.

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