Skip to main content
Glama
uk-kd

operbots-mcp

by uk-kd
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Добавить материал

knowledge_add_document

Add text, extracted file content, or a URL to a knowledge base. The material enters a pending state and is processed in the background; retrieve it later.

Instructions

Кладёт в базу текст, извлечённый текст файла (source=file) или страницу по ссылке. Разбор идёт в фоне: сразу после добавления материал в состоянии pending, проверьте его позже через knowledge_list. Повторный вызов создаёт дубликат, а не обновляет прежний материал.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlNoСсылка на страницу: панель скачает её и вырежет разметку.
baseYesБаза знаний: название или идентификатор.
caseNoДело: название или идентификатор. Если не указать, берётся дело по умолчанию, иначе последнее открытое в панели.
textNoТекст материала. Нужен, если ссылка не задана.
titleNoНазвание материала.
sourceNoИсточник материала. Для file передайте извлечённый текст в text; без source вид определяется по url.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.0
    • addedInput schema / properties / source
      Added value: +{
+  "description": "Источник материала. Для file передайте извлечённый текст в text; без source вид определяется по url.",
+  "enum": [
+    "text",
+    "url",
+    "file"
+  ],
+  "type": "string"
+}
  2. First observedv0.1.1

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare non-idempotent, non-destructive, open-world behavior, but the description adds the crucial consequence: asynchronous pending state and duplicate creation on re-invocation. That is real behavioral context beyond the structured hints.

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?

Three tight sentences, front-loaded with the action, followed by lifecycle and duplicate warnings. No filler.

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

Completeness4/5

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

With no output schema, the description covers the async lifecycle and where to verify results (knowledge_list), which is the key missing context. It does not detail error cases or base/case resolution, but the schema describes the default case behavior.

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 100%, so baseline is 3, but the description ties parameters together by explaining that source=file requires the extracted text in `text`, and that without `source` the type is inferred from `url`. This cross-parameter logic adds value beyond the per-field schema text.

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

Purpose4/5

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

States a specific verb ('кладёт в базу') and resource (текст, извлечённый текст файла, или страница по ссылке), making the sources explicit. It doesn't explicitly distinguish itself from siblings like knowledge_save or knowledge_document_update, though it does point to knowledge_list for follow-up.

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

Usage Guidelines4/5

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

Gives clear operational context: parsing runs in the background, the material lands in 'pending', and status should be checked later via knowledge_list. It also warns that a repeat call creates a duplicate rather than updating. It stops short of stating when to prefer this over knowledge_save/knowledge_document_update.

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