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

Annotations already declare read-only, idempotent, open-world, non-destructive, but the description adds substantial behavior: sections capped at 200,000 characters, cleanup of TOC/page numbers/XBRL/HTML with tables preserved as rows, the 404 SECTION_INCORPORATED_BY_REFERENCE outcome, and a full billing model ($0.02 USDC via x402, charged only on returned results, free on 400/4xx/5xx).

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?

Front-loaded with concrete question examples and the core 'returns one section' statement, and every paragraph carries needed content (lookup modes, cleanup, citation, limits, pricing). It runs long, but for a paid tool with a non-obvious billing model and cleanup semantics, the length is largely justified rather than padded.

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?

No output schema exists, yet the description explains the return shape (clean text section, tables as rows, citation metadata with filing date, fiscal period, accession number, sec.gov link), size limit, error semantics, and cost. An agent has everything needed to call and interpret results.

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 100%, so the baseline is 3. The description adds contextual meaning beyond the schema: fiscal_year is framed as '2001 on' and motivated by comparing risk-factor changes, and accession_number is linked to the free sec_list_filings tool that enumerates them.

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 and resource: 'Returns exactly one section of a US public company's 10-K (annual) or 10-Q (quarterly) report from SEC EDGAR as clean text.' It explicitly enumerates the section types and distinguishes itself from the sibling sec_list_filings by name, so an agent can route correctly without opening schemas.

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 names when to use it (investment research, due diligence, competitor analysis, risk monitoring), how to select an earlier year via fiscal_year for comparison, and the alternative sec_list_filings for enumerating filings and their sections. It even describes the fallback behavior when a section is incorporated by reference.

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