Save a SQL WHERE expression as a named custom signal the caller can reference by name in future scans.
| Name | Required | Description | Default |
|---|---|---|---|
| expr | Yes | SQL WHERE expression. Same grammar as scan `q`. | |
| name | Yes | Snake_case identifier. | |
| description | No | Optional human description. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries full burden. It does not disclose whether the tool overwrites existing signals, requires permissions, or has side effects. The only behavioral context is that the expression uses the same grammar as scan q.
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 a single front-loaded sentence with no redundant information. Every word serves a purpose, making it concise and easy to parse.
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 core purpose adequately but lacks details about return values, error cases, or lifecycle implications (e.g., whether duplicate names are allowed). For a creation tool with no output schema, slightly more context would improve completeness.
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%, but the description adds value beyond schema: 'Snake_case identifier.' for name, 'Optional human description.' for description, and 'Same grammar as scan `q`.' for expr, which clarifies the syntax. This extra context improves usability.
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 verb 'save' and the resource 'SQL WHERE expression as a named custom signal', and it distinguishes the tool from siblings by specifying the result is referenceable in future scans.
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 does not provide guidance on when to use this tool versus alternatives like tickerbot_update_custom_signal or tickerbot_delete_custom_signal. It only mentions future scans but lacks explicit when-to-use or when-not-to-use criteria.
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.
Most tools target distinct resource-action pairs, but get_ticker and get_ticker_history overlap (both return a single historical row via asof), and the four subscribe_* tools are thin wrappers around create_webhook, creating some ambiguity. Detailed descriptions mitigate but don't eliminate confusion.
The tickerbot_ prefix and verb_noun pattern are consistent (create_*, get_*, list_*, delete_*, update_*), but subscribe_* deviates from create_* for webhooks, and scan/search_news are bare verbs. Overall predictable.
35 tools is excessive for the domain; many could be consolidated (e.g., four subscribe_* variants into a single parameterized webhook creator, get_ticker/get_ticker_history into one). The breadth of data types justifies some volume, but this exceeds the 25-tool threshold for coherence.
Full lifecycle coverage for universes, custom signals, and webhooks; extensive read-side for tickers, series, bars, events, news, and scans. No critical dead ends: anything creatable can be updated/deleted/tested, and data lookups have appropriate query tools.
