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

The readOnlyHint annotation already indicates a safe read operation, lowering the burden. The description adds the meaningful limitation that OCR is not supported, which is valuable behavioral context. However, it does not disclose other behavioral traits such as error handling, rate limits, or what happens when a PDF cannot be parsed, so it offers moderate value beyond annotations.

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 extremely concise: two short sentences, no filler. The key information (what it does, input methods, and the OCR limitation) is front-loaded and every word earns its place. Ideal structure for quick agent parsing.

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 relatively simple extraction tool, the description covers the core function, input alternatives, and the critical OCR limitation. The absence of an output schema means the description could have specified the return format, but the tool name and verb 'extract text' make it reasonably clear. The optionality of parameters (with no required fields) is not fully clarified, but the description implies at least one of url or data must be provided.

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 is 100%, so the baseline is 3. The description's mention of 'url or base64 data' mirrors the schema fields but adds little beyond what the schema already states. It does not enrich understanding of headers or maxChars beyond their schema descriptions, so no extra semantics are provided.

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 extracts text from PDFs, with the specific input methods of URL or base64 data. It distinguishes itself from sibling tools like fetch_extract or html_to_markdown by specifying PDFs and the OCR limitation, making its purpose unmistakable.

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 a clear exclusion: 'No OCR — text-based PDFs only,' signaling when not to use this tool (scanned/image PDFs). However, it does not explicitly mention alternatives for those cases, nor does it elaborate on when to prefer one input method over the other, so it falls short of full explicit when/when-not guidance.

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