extract

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

With no annotations, the description carries the transparency burden. It explicitly states this is non-LLM Firecrawl extraction, which is a meaningful behavioral detail, and says it returns JSON. It does not mention network/auth/failure behaviors, but this is a low-side-effect extraction tool and the description covers the most useful behavioral points.

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 compact, front-loads the purpose, and every sentence adds needed information: schema format, selector syntax, supported selector types, and return type. There is no filler or redundancy.

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 2-parameter tool with an output schema, the description provides enough detail to construct a valid call, including the tricky schema parameter. Its main gap is lack of explicit integration guidance, such as when to choose this over extract_links/table_extract, but the implementation details are clear.

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 coverage in the input schema is 0%, so the description must compensate. It does: it documents that schema is a JSON string with CSS and XPath syntax and provides concrete selector examples. URL semantics are not detailed, but they are obvious enough from the tool context.

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 clearly identifies this as schema-driven extraction: 'Извлечение по схеме' with CSS/XPath selectors, returning JSON. It is specific about what the tool does and implies distinction from siblings like extract_links or table_extract, though it does not name any alternative explicitly.

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 intended use is implied: use this when you need structured field extraction from a page via CSS/XPath schema. However, there is no explicit 'when to use vs when not to use' guidance and no mention of alternatives, so the agent has to infer the selection decision.

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