첨부 본문 읽기

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

Discloses caching behavior (reuses downloaded files), auto-download if list missing, and non-extractable formats (body empty). Annotations give readOnlyHint=false and openWorldHint=true, and description aligns without contradiction, adding context 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 a single, efficient paragraph of 4 sentences, front-loading the main purpose and covering key behaviors without waste.

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?

Covers formats, ZIP handling, streaming, and caching, but lacks explicit description of the return value structure (e.g., fields like text, truncated, savedPath). For a tool with no output schema, this is a minor gap.

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%, but description adds significant context: explains index usage from download_attachments response, offset/maxChars for streaming, and bidNtceNo to match the notice.

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 verb 'reads' the text body of a file, specifies the resource (files from download_attachments list), and distinguishes from siblings by naming download_attachments and get_bid_attachments.

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 tells when to use this tool vs alternatives ('목록을 먼저 받으려면 download_attachments를, 첨부 URL만 필요하면 get_bid_attachments를 쓴다.'), and explains how to handle long documents with offset/maxChars.

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