notion_extract_file_text

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

With no annotations provided, the description carries full responsibility for behavioral disclosure. It excels by detailing response truncation (200 KB ceiling, page-boundary truncation, trailing marker), silent dropping of out-of-range pages, OCR auto behavior with a 20-char threshold, error conditions ('ocr_error'), and the distinction between native and OCR extraction. These details go far beyond what the schema or annotations reveal.

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 long but densely informative, with every section providing necessary operational detail. It is front-loaded with the core purpose and then structured into paragraphs and enumerations for source schemes, return format, page specs, mode, and OCR, making it navigable despite its length.

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?

Despite the presence of an output schema, the description goes beyond it by explicitly listing the returned JSON fields and explaining truncation behavior. It covers all four parameters, source access, mode semantics, OCR fallback conditions, and error signaling, leaving no material gap for an agent to invoke the tool 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?

Since schema description coverage is 0%, each parameter is thoroughly explained in prose: source includes scheme-specific examples, pages uses a pdftotext-style grammar with concrete examples, mode enumerates 'text', 'layout', and 'tables' with explanations, and ocr documents 'auto', 'off', 'force', and 'llm' with detailed behavior. This fully compensates for the absent schema descriptions.

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 states the tool's function: "Extract text from a PDF anywhere notion-mcp can reach" and distinguishes it by noting it does so "without moving the bytes over MCP." It also specifies supported source schemes and references companion tool notion_list_files_on_page, making the resource and scope unambiguous.

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 description provides clear contextual guidance: it explains the acceptable source schemes, how to obtain block IDs (via notion_list_files_on_page), and when to use different modes and OCR settings. However, it does not explicitly contrast with alternative sibling tools (e.g., notion_download_file) or state when not to use this tool, so it falls short of full alternative-based guidance.

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