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

With no annotations, the description carries the full disclosure burden. It is transparent about the main side effect — the tool 'запускает сбор' (launches collection) — and documents the onlyLinks=true escape hatch that returns links without collecting. However, it does not explain what launching collection entails downstream (e.g., scheduled runs, group membership, how to stop it), even though siblings like parsee_stop and parsee_status hint at async behavior.

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?

Two compact sentences deliver the core action, the use case, and the key option with no filler. The onlyLinks hint is appended after the prose rather than structured, but it earns its place because it documents the most important behavioral switch.

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 3-parameter tool with an output schema, the description covers the main purpose and the onlyLinks behavior adequately. Gaps remain: 'limit' semantics are absent, and the collection-launching behavior is not connected to the tool ecosystem (how to monitor or stop it), which matters given related siblings parsee_wait, parsee_status, and parsee_stop.

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?

At 0% schema description coverage, the description must compensate for bare schema properties. It adds meaning to url (accepted link types: category, search, brand, seller) and to onlyLinks (return links only, without collection), but leaves 'limit' completely unexplained — an agent cannot determine whether it caps cards, pages, or something else.

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 uses a specific verb ('разворачивает' — expands) with a clear resource (links to categories, search results, brands, sellers) and outcomes (a list of cards and launched collection). It also distinguishes itself from the page-by-page scraping approach and from sibling parsee_parse_urls by framing this as whole-market capture.

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 phrase 'Так берут рынок целиком, вместо перебора выдачи по одной странице' provides clear guidance on when to use the tool: when the goal is to capture the entire market rather than iterate search pages one at a time. It implies the alternative approach but does not explicitly name a sibling tool as the counter-option.

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