cluster_buysFind issuers where multiple distinct insiders independently bought with their own money (code P) inside a window - a signal raw EDGAR cannot answer. Sorted by total value.
| Name | Required | Description | Default |
|---|---|---|---|
| window_days | No | Lookback window in days, default 30. | |
| min_value_usd | No | Minimum combined buy value per issuer in USD. | |
| min_distinct_insiders | No | Minimum distinct buyers per issuer, default 2. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and idempotentHint=true, so safety profile is covered. The description adds useful behavioral context: filtering by code P, sorting by total value, and the derived nature of the signal. However, it does not mention return format, pagination, or default behavior, so it adds moderate but not deep transparency.
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 one concise, front-loaded sentence with no wasted words. It states the core action, criteria, unique value, and sorting in a clear structure.
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 should clarify return values, but it only says 'Find issuers' without specifying the exact output structure (e.g., list of issuers with total values, fields included). It also does not mention default parameter behavior, though the schema covers defaults. For a read-only aggregation tool, it is adequate but has gaps in return-value detail.
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 100%, with each parameter (window_days, min_value_usd, min_distinct_insiders) having a clear description. The tool description adds minimal extra parameter context (e.g., relating to total value and window), but the schema already carries the semantic weight, so a baseline 3 is appropriate.
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 uses a specific verb ('Find') and clearly identifies the resource (issuers with multiple distinct insiders independently buying with their own money, code P, within a window). It distinguishes itself from sibling tools like get_insider_trades by highlighting the cluster signal that raw EDGAR cannot answer and includes a sorting detail.
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 provides clear context for when to use the tool (when you need cluster signals of independent insider buys), and the phrase 'a signal raw EDGAR cannot answer' hints at its unique analytical role. It does not explicitly name alternative tools or state exclusions, but the context is sufficient for selection.
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 has a clearly distinct purpose: per-form search tools (get_insider_trades, get_material_events, get_planned_sales, get_stakes), cross-feed signals (cluster_buys, planned_vs_executed, trades_before_events), and support utilities (company_profile, describe_coverage, find_company, list_recent_filings). The only slight overlap is company_profile vs. get_insider_trades, but company_profile is explicitly an aggregator that routes to detailed tools, eliminating ambiguity.
Most tools follow a verb_noun pattern, especially the get_* family (get_insider_trades, get_material_events, etc.). However, three tools deviate: company_profile (noun_noun), planned_vs_executed (phrase with 'vs'), and trades_before_events (noun_phrase). These are still readable and clearly named, but they break the otherwise consistent convention.
11 tools is well-scoped for the domain of insider trading analytics. It provides a complete set of per-filing-type search tools, cross-feed signals, and support utilities without redundancy or bloat. The count is within the ideal 5-15 range and feels justified.
The tool set covers the full lifecycle of insider data: entity resolution (find_company), orientation (describe_coverage), all major SEC forms (3/4/5, 8-K, 144, 13D/13G) via dedicated search tools, and advanced cross-feed analytics (cluster_buys, planned_vs_executed, trades_before_events). No obvious gaps are apparent for the stated purpose.