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

With no annotations, the description carries the full behavioral burden and does so thoroughly: it lists input methods (GET URL, POST multipart/raw/JSON base64), output fields, refusal before payment on bad input or model outage, and pricing ($0.009 USDC via x402). This gives the agent a clear picture of cost, error handling, and return format.

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 a single dense paragraph that front-loads the usage scenario, then covers input/output/errors/pricing. Every sentence is informative, though slightly more structure (e.g., bullets) could improve readability. No redundant filler.

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 complex document-extraction tool with no annotations and no output schema, the description covers the essential context: supported formats, input encodings, output fields, payment model, and failure behavior. It omits file size limits or timeout behavior, but those are minor for selection and invocation.

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 two parameters are documented, but the description adds critical detail not captured by the schema: how to POST a file using multipart 'file', raw body, or JSON contentBase64+filename. It also gives an example URL query. This compensates for the schema's inability to represent POST body encodings.

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?

States a specific verb ('extract') and resource (Korean HWP/HWPX, PDF, DOCX or web page) and distinguishes itself from plain text tools by requiring 'key facts, not just its text'. It also names the structured JSON output, making the purpose unambiguous against siblings like convert_to_markdown or web_read.

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?

Provides a clear usage condition: 'Use when an agent needs the key facts of a document, not just its text.' It does not name alternative tools or explicitly state when not to use it, but the context is sufficient to select it over text-only readers.

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