Пакетное чтение

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds substantial non-structured behavior: cache hits return instantly without a browser, inter-navigation rate limiting guards against CAPTCHA, batches of ≥8 URLs run in a thread pool with per-thread browsers, and max_chars truncates only the response, not the crawl. This is richer than typical annotation coverage.

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?

Dense but front-loaded: purpose, then cache/rate-limit/parallel behavior, then an example, then when/not-when. The dated benchmark timings (36.4s/30.3s/45.9s) are somewhat verbose, but they justify the tuning advice and are not pure 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?

An output schema exists, so return values need not be explained, yet it still notes the '--- URL: ...' text separators. Given four parameters, no schema descriptions, and a parallel/cached execution model, the description supplies everything an agent needs to call it correctly.

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 0%, so the description must carry all four parameters — and it does: urls (scale guidance), max_chars (concrete ranges 4000-100000 with measured tradeoffs), article_only (Trafilatura extraction excluding menus/banners), and max_parallel (explicit cap on auto-detected workers). A worked example demonstrates combined usage.

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?

States a specific verb and resource ('Открывает НЕСКОЛЬКО URL в одном браузере') plus the scale it targets (30-50 sources, one call instead of cold starts). An agent can immediately distinguish it from fetch_page and the other fetch-adjacent 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?

Contains explicit 'КОГДА' and 'НЕ КОГДА' sections: use for 10-50 URLs after research/crawl/map_site; use fetch_page for 1-2 pages; gather URLs first via research, sitemap, map_site. Alternatives and exclusion conditions are named outright.

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