get_submissions

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered; the description goes further by disclosing that the payload is byte-faithful ('unchanged', names/tickers/addresses exactly as given) and that numeric precision is preserved by falling back to the SEC's original text, listed in `numbers_as_text`. It also describes the shape of `older_files`. The only notable gap is that it never says what happens on an invalid ticker or how large the recent table is.

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 identity and immutability guarantee is front-loaded in the first sentence, then return structure is layered on. It is dense but every clause carries information; only the line-wrapped formatting and the slightly buried `numbers_as_text` explanation cost it a point.

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 an output schema present, the description needn't detail return values, yet it usefully explains the nested `older_files` entries and the numeric-text fallback that a schema alone would not convey. For a two-parameter read tool it is close to complete; the missing pieces are error behavior and the identifier format for `cik_or_ticker`.

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 description coverage is 0%, so the description must carry the parameters. It fully explains `include_older_files` (returns each file in `older_files` as {name, payload, numbers_as_text}, in listed order), but `cik_or_ticker` receives no treatment at all — no format, casing, or whether zero-padded CIKs are accepted, despite being the sole required parameter.

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?

States a specific resource (the SEC submissions document for one company) and its key property (returned unchanged), which is enough to separate it from get_companyfacts / get_companyconcept that return derived data. It does not, however, name any sibling or explicitly contrast itself with list_filings, so the differentiation is inferential rather than stated.

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?

There is no explicit 'use this when...' routing versus lookup_company or list_filings, but the description does give one actionable condition: filings older than the recent table live in `filings.files`, and `include_older_files` fetches them. That is useful implied guidance for the parameter decision, though nothing tells the agent when to prefer this tool over list_filings for filing data.

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