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

Annotations already declare readOnlyHint=true, and the description's 'Read the text' is fully consistent (no contradiction). The description adds genuine behavioral context beyond annotations: the business-plan gate, the max_chars truncation limit, and the exact input format scope.

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?

Core information (purpose, formats, use cases) is front-loaded and each clause earns its place. Minor redundancy: 'Business plan only' is repeated by the trailing '[requires the business plan]' tag, and the opener echoes the title.

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 moderate-complexity file-ingestion tool with no output schema, the description covers purpose, formats, plan constraint, truncation limit, and the conversion workflow — enough for correct invocation. The main gap is the exact return shape (plain text vs. structured), which is left inferable.

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?

With 100% schema coverage the baseline is 3, but the description adds value for the `file` parameter by specifying which formats are accepted — something the schema's generic 'The document to read' omits. It also reinforces the max_chars behavior ('Returns up to max_chars characters'), which helps the agent size the request correctly.

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?

Specifies a concrete action (read/extract the text of the user's document), enumerates the supported formats (PDF, TXT, CSV, Markdown, JSON), and ties the tool to clear use cases (answer questions, summarize, use facts later). The chat-oriented framing distinguishes it from sibling extraction/conversion tools like pdf_to_text, and the Word-file exclusion clarifies scope.

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?

Explicitly routes the Word-file edge case to convert_word_to_pdf before using this tool, which is strong when-to/not-to guidance. However, it stops there — it doesn't address alternatives for other scenarios (e.g., pure extraction via pdf_to_text, OCR for scanned PDFs via pdf_ocr), leaving some routing to inference.

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