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

Annotations only declare readOnlyHint and openWorldHint, but the description adds non-obvious operational facts: traffic goes through a residential proxy, each successful call costs $0.002 in USDC via x402 on Base/Solana/Arc, and failed calls are not charged. The billing and proxy disclosure is exactly the kind of behavior an agent cannot infer from structured fields and would want before invoking.

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?

Front-loaded with the core 'what you get' clause, then input forms, then alternatives, then pricing — a sensible order with no filler sentences. It is dense, with a long parenthetical field list and two embedded alternatives, but every element carries information an agent needs; the title's truncation ('the products the public') is the only real sloppiness.

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 two-parameter, read-only scraper with full schema coverage and an output schema, nothing material is absent: scope (US), result size (~10), input forms, proxy routing, cost model, and failure billing are all stated. Return-field detail is arguably redundant with the output schema but costs little.

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% and the schema already explains both the category slug/URL forms and that categoryId is an optional digit id looked up from the slug. The description restates the slug examples and the id lookup, adding only light reinforcement rather than new meaning, so the baseline 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?

Names a specific verb/resource pair — TikTok Shop (US) category products — and enumerates exactly what comes back (title, price, original price, rating, review count, units sold, shop name, brand, link, plus recent reviews and category tree). It also names two sibling tools and the needs they serve, so an agent can separate this from social_tiktok_comments and social_tiktok_hashtag_analytics without opening a schema.

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?

Gives concrete positive routing guidance: the 'Related tools on this server, for a different need' clause explicitly assigns comments and hashtag stats to the siblings, and it tells the caller the two accepted input forms. What is missing is a negative boundary — e.g. that this returns only the top ~10 page products rather than full catalog search results or individual product detail, which is implied by '(about 10)' but never stated as a limitation.

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