Filing Text

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safe-read profile is covered. The description adds real context beyond that: HTML-to-text conversion with ' | ' cell joining, 'next_offset' continuation semantics, 20,000-char default pages, up to 10 find matches, and the document-list fallback when no document is named. It does not repeat the annotations, but it also doesn't cover rate limits or SEC-specific access constraints. A 3 reflects solid added context on a tool whose safety profile the annotations already carry.

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, then pagination strategy, then caveats; every sentence carries information and nothing is decorative. It is a single dense block of ~120 words that would scan faster as short bullets, which is the only real cost.

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?

There is no output schema, and the description compensates well: it describes the first page's 'sections' list, the document list shape with document types, 'next_offset', and the image count in the response. Given a long-document reader with 8 optional params, that is close to complete, though the exact response envelope is still only sketched.

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%, so the schema already documents all 8 parameters, and the default 3 applies. The description goes slightly beyond the schema by explaining the 'next_offset' round-trip pattern and what a missing 'document' yields (a document list), which is genuinely useful interaction semantics rather than restatement.

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 ('Read the text of an SEC filing document') and then enumerates the concrete document types covered (10-K, 10-Q, 8-K, proxy, EX-99.1 exhibit). It also implicitly separates itself from the sibling search/list tools by describing them as the sources of the 'url' argument rather than alternatives for reading text.

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 the agent: pass 'url' from sec_recent_filings or sec_full_text_search, or 'accession' plus 'ticker'. It also gives a decision rule for the optional modes (use 'section' to read one part, 'find' to locate passages, 'offset' to continue) which tells the agent which control to reach for and when.

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