Digest for a filter over the last N days: material 8-K events, insider (Form 4) activity, new registrations, and periodic reports. Best summary signal for a desk.
| Name | Required | Description | Default |
|---|---|---|---|
| cik | No | ||
| days | No | Lookback days (default 7). | |
| form | No | ||
| item | No | ||
| ticker | No | ||
| company | No | ||
| minEventScore | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, and the description does not disclose behavioral traits such as authentication requirements, rate limits, or whether inputs are required. It also fails to describe the output format, which is critical given no output schema.
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 very concise at two sentences with no filler, though it could be slightly more structured. Every sentence provides relevant information.
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?
Given the tool has 7 parameters (most undocumented), no output schema, and no annotations, the description is incomplete. It fails to explain filtering options, required parameters, output structure, or limitations.
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 only 14% (only 'days' has a description). The description mentions 'last N days' linking to 'days' but does not explain the other 6 parameters (cik, ticker, company, form, item, minEventScore), leaving their semantics unclear.
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 clearly states the tool provides a digest of multiple filing types (material 8-K, insider activity, new registrations, periodic reports) over a time filter. It distinguishes from siblings by being a composite summary rather than a specific search or monitoring tool.
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 says 'Best summary signal for a desk,' implying use for quick overviews, but it provides no explicit guidance on when not to use it or how it compares to alternatives like search_filings or insider_activity.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct aspect of SEC filings research: company_watch for a company overview, filing_digest for recent summaries, insider_activity for insider transactions, search_filings for ad-hoc full-text search, and whats_new_since for incremental updates. No ambiguity between them.
All tool names use descriptive snake_case with a clear verb_noun or noun_verb pattern (e.g., company_watch, insider_activity, search_filings). The naming style is consistent and intuitive.
With 5 tools, the server is well-scoped for its domain of SEC EDGAR data access. Each tool serves a clear purpose without unnecessary overlap, and the count is appropriate for the feature set.
The tool set covers key use cases: company monitoring, insider activity, full-text search, and incremental updates. Minor gaps could include direct retrieval of a single filing by accession number or more granular filtering, but the core workflows are complete.