download_sec_report

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

With no annotations, the description carries full behavioral burden. It clearly discloses that PDF exhibits are skipped and never parsed, that HTML exhibits are included by default for 6-K/8-K, and that a successful download must be followed by parse_sec_report. It also notes the pdf_not_supported limitation, providing useful operational transparency.

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 well organized with purpose, strategy, critical rules, and args. However, there is some redundancy: 'PDF exhibits are skipped, not parsed' appears twice, and the proactive-call warning overlaps with critical rule 1. Still, the structure is clear and all content is relevant.

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?

The description provides fallback triggers, post-download parse requirements, exhibit handling rules, and parameter semantics. An output schema exists, so return value details are not necessary in the description. This is complete enough for an agent to use the tool correctly within the sibling workflow.

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 description coverage is 0%, so the description fully compensates by giving concrete examples: ticker like 'AAPL', form types like '10-K' and '6-K', report_date as fiscal period end date or fiscal year, and include_exhibits with context-dependent defaults plus the note that PDF exhibits are never parsed.

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 uses a specific verb and resource: 'Download a SEC report from EDGAR for the specified company, form type, and report date.' It also mentions exhibit handling for 6-K/8-K, which adds detail and distinguishes this tool from siblings like keyword_search and parse_sec_report.

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 <strategy> block explicitly states to invoke this tool 'ONLY as a fallback when keyword_search, get_report_pages, or get_report_toc explicitly returns a "file not found" error' and includes 'Do not proactively call this tool without receiving an error first.' Critical rule 1 reinforces the search-before-download ordering, making the usage conditions unambiguous.

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