Skip to main content
Glama
aidvizhhub

camoufox-research

by aidvizhhub
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Извлечение полей

extract
Read-onlyIdempotent

Use JSON schema to retrieve fields by CSS/XPath selectors or LLM hints for fragile markup.

Instructions

КОГДА: нужны конкретные поля страницы — при стабильной вёрстке селекторами (CSS/XPath) или из текста через llm=True, когда вёрстка хрупкая и селекторы отваливаются. ЧТО: schema — JSON-объект (можно строкой для совместимости): {"поле": "css:.price"} или {"поле": {"selector": ".price", "attr": "text|href|src"}}; llm=True — {"поле": "подсказка"} и нужен LLM (DeepSeek/Ollama), иначе честный ответ «недоступен». НЕ: нужен сплошной текст → fetch_page / batch_fetch; таблицы → table_extract; не знаешь селектор → сначала snapshot.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
llmNo
urlYes
schemaYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.21.1
    • addedInput schema / properties / schema / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": true,
+    "type": "object"
+  }
+]
    • removedInput schema / properties / schema / type
      Removed value: -"string"
  2. Changed1 schema field changedv0.18.1
    • addedInput schema / properties / llm
      Added value: +{
+  "default": false,
+  "title": "Llm",
+  "type": "boolean"
+}
  3. Addedv0.2.0

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already cover readOnly/openWorld/idempotent/non-destructive, but the description adds real behavioral context beyond them: llm=True requires an LLM backend (DeepSeek/Ollama) and otherwise returns an honest 'unavailable' answer, and schema is accepted as a JSON string for compatibility. Minor gaps remain (rate limits, whether extraction is bounded per page).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded labeled sections (КОГДА / ЧТО / НЕ) pack the routing decision, format spec, and exclusions into a few dense lines with no filler. Every clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With an output schema present, return values need not be described; the description instead covers selection criteria, parameter encoding, backend dependency, and sibling alternatives, which is complete for a 3-param extraction tool. The reference to 'snapshot' (absent from the sibling list) is the only nit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must carry the load, and it does: it documents the schema parameter's css:/XPath prefix syntax, the {selector, attr: text|href|src} object form, and the llm hint form, plus llm=True's backend dependency. Only url is left unexplained, which is self-evident.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The 'ЧТО' block states a precise verb+resource (extract named page fields) and immediately distinguishes the two modes (selector-based vs llm=True). It is trivially separable from siblings like fetch_page or table_extract.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The 'КОГДА' and 'НЕ' blocks give explicit when-to-use, when-not, and name the concrete alternatives (fetch_page / batch_fetch for raw text, table_extract for tables, snapshot when the selector is unknown). Routing is unambiguous.

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

Deploy Server

Other Tools