list_filings

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

No annotations are provided, so the description carries the burden. It discloses ordering (newest first), filtering, and the prefix-matching behavior for form types. It also states the return content (accession numbers). However, it does not mention whether the operation is read-only (likely safe but unstated), whether authentication is needed, or any pagination/limits beyond the default limit parameter. It gives some behavioral context but not comprehensive coverage.

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-structured: a front-loaded purpose sentence, a list of form-type definitions, the prefix behavior, and a closing note about the return value's use. It is longer than minimal but each sentence adds value—especially the form-type glossary, which is genuinely helpful for an agent. No wasted words.

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 covers the essential output (accession numbers) and the form filter, but it omits details on the 'since' parameter (date format?), 'limit' semantics, and whether the 'company' parameter expects a ticker, CIK, or name. It also does not reference find_company as a prerequisite for obtaining a company identifier, which is a likely need. The tool is moderately complex (4 params, no annotations), so more explanation is warranted.

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 0%, so the description must compensate. It thoroughly explains the 'form' parameter, including what each common form type means and the prefix-matching rule. It implicitly covers 'company' (a company identifier) and mentions 'limit' indirectly via the default in schema, but it does not explain 'since' (likely a date filter) or how 'limit' behaves (e.g., maximum, pagination). Partial compensation only.

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 clear verb+resource statement: 'List what a company has filed with the SEC, newest first.' It specifies the resource (SEC filings), the ordering (newest first), and distinguishes itself from read_filing_section by mentioning accession numbers as its output. It also enumerates form types with plain-language meanings, giving an agent enough to decide if this is the right tool 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 implies usage: it is the tool to list filings before calling read_filing_section, and it explains form filters. However, it never explicitly says when not to use it or contrasts it with search_filings (which likely handles keyword search). It gives a hint that this is for getting accession numbers, but lacks an explicit 'use search_filings for full-text' or 'use find_company first' note.

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