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

Annotations cover safety (readOnly, idempotent, non-destructive), and the description adds substantive behavior beyond them: items are located by document headings rather than literal string matching, so TOCs and cross-references are never mistaken for sections. It also explains the not_located semantics with concrete causes (Item 1C pre-2023, 10-K/A with only Part III, unreported 8-K items, or missed headings), which no annotation conveys.

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 purpose and return shape, then fallbacks and caveats in descending priority — the ordering is correct. It runs longer than most definitions, but nearly every sentence (heading-detection, not_located causes, sibling routing) carries non-redundant information; only the entry-field enumeration slightly overlaps the output schema.

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 one-parameter read tool with an output schema and full safety annotations, nothing an agent needs is missing: valid inputs, sibling routing, not_located interpretation, and fallback behavior are all covered. Return values are explained even though the output schema already exists, which is surplus rather than a 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?

With 0% schema coverage on the single required parameter, the description must carry the load, and it does: it names the valid form types and gives a concrete accession-number example format ("0000320193-25-000079"). It stops short of stating the format rules explicitly (10-digit filer prefix, year, sequence), which would have made it a 5.

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?

Opens with a specific verb+resource ('List the Items of a 10-K, 10-Q, 8-K or 20-F') and immediately bounds the deliverable: which sections exist and where. It also enumerates the per-entry fields (item, part, SEC title, filer heading, length, highlight_url), so an agent knows exactly what it gets without opening the output schema.

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 routes: 'Read one with get_filing_item' for section text, and 'Other forms (6-K, 40-F, DEF 14A, S-1...) have no numbered Items: read them with search_document or get_document.' It even covers the not_located edge case and states get_filing_item still answers for those, so both the primary and fallback paths are named.

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