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

The description contributes substantial behavior beyond the annotations: per-page billing with failed fetches free, per-item provenance, and the privacy note 'URLs are not logged'. That is genuinely useful information an agent cannot get from readOnly/idempotent/destructive hints. Minor tension: it clearly reaches arbitrary external sites while openWorldHint is false, but the core safety hints align, so no hard contradiction is recorded.

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 purpose is front-loaded and useful, but the second half enumerates the entire response shape (emails[], phones[], social{}, addresses[], pages[], summary{}, data_confidence, estimated_items[], sources[], warnings[]...), which duplicates the output schema and pads the definition. A tighter definition would let the output schema carry that load.

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 a full output schema, rich annotations and complete parameter docs, the description is nearly complete for correct invocation: scope, cost model, privacy, and fetch behavior are all covered. The main omission is any explicit routing among sibling tools.

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 url, region, max_pages, include_social, respect_robots and follow_contact_pages are all documented in the schema. The description restates the max_pages semantics and region example without adding new meaning, so the baseline 3 applies.

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?

Strong specific verb and resource: 'Fetch a site's homepage and up to max_pages-1 contact/about pages and return every email, phone...'. It clearly tells an agent this is a single-site contact scraper. It does not explicitly differentiate from siblings like extract_contacts_bulk, extract_from_html, or find_social_profiles (whose territory partially overlaps with the social{...} output), so it stops short of a 5.

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?

Usage is implied by the detailed scope and an inline example ('url noahsarch.tech, max_pages 3, region AE') plus a caveat that respect_robots=false is only for owned sites. However there is no explicit 'use this when X, prefer sibling Y when Z' routing, so the agent must infer when to pick this over the bulk or HTML variants.

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