get_attachments

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

With no annotations, the description carries full burden. It transparently discloses the scraping-based approach and the kordoc conversion engine. It also mentions truncation and outline parameters, providing insight into limitations. However, it does not detail failure modes, rate limits, or the exact behavior when scraping fails.

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 sentences that convey the purpose, mode options, file types, and technical background. Every sentence adds essential information 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 complexity (2 modes, multiple file types, scraping-based) and no output schema, the description covers key aspects. However, it lacks details about the return format for list mode (e.g., what fields are in the attachment list) and the exact structure of the extracted markdown. This minor gap prevents a perfect score.

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 the description adds significant value beyond the schema. It explains the mode-dependent behavior of index/filename, the special handling of ZIP attachments via zip_index, and the purpose of truncate_at and outline_max_items. This allows an agent to understand parameter interactions and defaults.

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?

Description clearly states the two modes (list/extract) and the types of attachments (HWP/PDF/DOCX/XLSX). It distinguishes the tool as a specialized attachment handler for DART disclosures, which is distinct from other sibling tools that focus on financial data or document downloads.

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 explains the two modes and when to use each ('list' for listing attachments, 'extract' for downloading and converting to markdown). It provides context that the tool uses DART viewer scraping due to missing official API endpoints. However, it does not explicitly compare against sibling tools like 'download_document' or provide when-not-to-use guidance.

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