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

With readOnlyHint already covering safety, the description adds rich behavioral context: truncated responses with next_offset continuation, character-based pagination with sensible defaults (50K chars ≈ 12,000 words), section-jump precedence over offset, and the fact that binary document entries are rejected. The document parameter surfaces that available documents appear in response metadata, and include_xbrl enumerates exactly which file types are returned. All consistent with readOnly/openWorld/idempotent annotations—no contradiction.

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?

Three tight, front-loaded sentences. The first states the core purpose; the second explains large-filing pagination with a concrete scale example; the third covers section jumping. Every sentence covers distinct functionality 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?

For a tool fetching potentially enormous filings, the description anticipates every practical edge case: long-document truncation (offset/next_offset), retrieval size limits (content_limit with rationale), navigation costs (section jump), and the XBRL noise problem on large filings. An output schema exists, so return-format documentation is not required here. The only minor gap—section matching semantics—is acknowledged and deflected cleanly via the outline-returning error behavior.

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?

Despite 100% schema coverage, the parameter descriptions add substantial non-obvious value: offset explains the char-based continuation contract with next_offset, section documents its precedence and error-recovery behavior ('On a miss, the error message includes the detected outline'), content_limit gives practical calibration anchors (12K words, when to raise to 200K), and include_xbrl enumerates concrete file patterns. These go well beyond restating parameter names.

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 opens with a specific verb+resource: 'Fetch a specific filing's metadata and document content by accession number.' It clearly establishes the accession-number addressing model that differentiates it from siblings like secedgar_company_search or secedgar_get_financials. The purpose is unambiguous even without opening the 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?

The description gives clear usage context: when to page with offset/next_offset ('10-K, S-1 can exceed 1M chars') and when to use section jumping instead. Cross-references in parameter descriptions route users to secedgar_company_search and secedgar_search_filings for obtaining the accession number. However, it stops short of explicitly stating when NOT to use this tool versus a named sibling—exclusions are implied rather than stated.

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