list_filings

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

Annotations only assert readOnlyHint=true and openWorldHint=true, so the description carries the behavioral burden — and it delivers: pagination (per_page default/max thrown in schema, but the description frames newest-first ordering), the semantics of an entry (accession number, amendment type, non-superseded transaction count), inclusive date-window behavior, alias precedence (per_page wins), and the plan-gating note. All of this is context annotations alone could not supply, and nothing contradicts the read-only/open-world hints.

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 front-loaded with the verb and primary use case in the first clause, then flows from result semantics to entry fields to alternatives to parameter trivia. Every sentence carries distinctive information — the only minor redundancy is that filters are mentioned twice (first and second sentence), but this is low-cost re-emphasis, not waste.

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?

With no output schema, the description correctly fills the return-value gap by enumerating what every entry carries (accession number, ticker/name, period of report, filed date, amendment type, non-superseded transaction count). Pagination, ordering, filter behavior, alias semantics, and sibling routing are all covered; nothing an agent needs to call this read-only list tool correctly is missing.

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 baseline is 3; the schema already documents every parameter with defaults (per_page=20, page=1, to=100), formats (YYYY-MM-DD), examples (CIK string with leading zeros), and alias precedence. The description adds value on top by grouping several params into a cohesive semantic idea: the filters ticker, CIK, and 'a from/to filed-date window', which is small but real framing benefit beyond the schema.

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 names a specific verb-resource pair ('List Form 4 filings') and immediately scopes it: optional ticker/CIK/date filters, paginated, newest-first, with per-entry fields enumerated. It explicitly distinguishes itself from get_recent_filings and get_transactions by pointing at their unique behaviors (no page parameter vs. individual trades), so an agent can disambiguate without opening sibling 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?

Gives explicit selection logic: 'Use this for a company's filing HISTORY', then names the alternatives with the condition that selects each — GET /v1/filings/recent for a live feed (explicitly noting it lacks a page parameter) and GET /v1/transactions when individual trades are needed. Also discloses that it is 'Not plan-gated', which is relevant access/cost context an agent can act on.

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