Extract Article Content

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

The description discloses detailed behavior beyond annotations: how HTML vs PDF detection works (Mozilla Readability, Content-Type, %PDF magic, citation_pdf_url meta, per-domain rules), tiered depth modes, best-effort nature, and private IP blocking. No contradiction with annotations (readOnlyHint, idempotentHint, openWorldHint all true).

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 concise and well-structured: front-loaded with the core purpose, then specific details about PDF detection, modes, and error handling. Every sentence adds value without redundancy.

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?

Given the tool's complexity (3 parameters, output schema provided), the description is complete. It covers behavior, modes, error handling, and detection logic. The output schema exists, so return value details are not needed in the description.

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?

The input schema has 100% description coverage, so the description adds limited value beyond the schema. However, it does provide helpful context for the 'mode' parameter by explaining 'abstract' as a cheap survey and 'metadata' as page count only, which enriches the schema's enum values.

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 'Fetch one public URL -> clean article text' and distinguishes itself from sibling tools like search and search_extract by focusing on single URL extraction. It details specific academic PDF handling and modes, making the purpose 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 explicit usage guidance: it explains when to use the abstract mode ('cheap survey to triage relevance before paying for full body') and notes that failures return errorInfo instead of throwing. It implies when not to use (e.g., for searching) by being a single-URL tool.

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