Today's top scored catalyst picks from the Catalyst Edge convergence model. Optional filters: conviction, sector. Free tier returns the top 3.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | max picks (default 25; free tier capped at 3) | |
| sector | No | filter by sector (substring match) | |
| conviction | No | filter by conviction level |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals the free tier returns only the top 3, which is useful. However, it does not explain sorting beyond 'top scored,' what a pick contains, or any rate limits beyond the tier cap. The temporal qualifier 'Today's' adds context, but additional behavioral detail is absent.
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 two sentences, front-loaded with the main purpose and immediately followed by filter and limit details. Every clause earns its place: 'Today's top scored catalyst picks' states what, 'Optional filters' previews parameters, and 'Free tier returns the top 3' conveys a key behavioral constraint. No redundancy or filler.
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?
For a simple retrieval tool with no output schema, the description covers the essential information: what it returns, when (today's), and a critical tier limitation. It does not describe the return structure, but given the low complexity and the wealth of schema details for parameters, this is largely sufficient. The lack of alternative tool references slightly reduces completeness, but the tool is straightforward enough that agents can invoke it correctly.
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 clearly described (limit, sector, conviction). The description restates 'Optional filters: conviction, sector' but adds no new meaning beyond the schema. It does not elaborate on conviction levels or limit behavior beyond what is already in the schema, so it meets the baseline but does not exceed it.
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 returns 'Today's top scored catalyst picks from the Catalyst Edge convergence model,' specifying both the resource (catalyst picks) and the temporal scope (today's). This distinguishes it from sibling tools like get_ticker_signal or get_sector_lean, which focus on individual signals or sector leans rather than a ranked pick list.
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 implies usage (retrieve top picks) and mentions optional filters, but provides no explicit when-to-use guidance or exclusions relative to sibling tools. It does not name alternatives like get_thesis or get_options_context, so an agent must infer context from the tool's purpose. The free tier cap is noted, which helps with invoking correctly.
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 addresses a clearly distinct purpose: list picks, per-ticker signal, narrative thesis, sector context, options context, and historical track record. While get_thesis and get_ticker_signal both focus on a single ticker, one is qualitative and the other is quantitative, so an agent can easily choose based on need.
All tool names follow the same get_<noun> pattern, using snake_case consistently. The nouns are descriptive (picks, options_context, sector_lean, thesis, ticker_signal, track_record), making the API predictable and easy to navigate.
Six tools is a well-scoped size for a specialized financial analytics server. Each tool earns its place by covering a distinct aspect of the domain without redundancy or bloat.
The tool surface covers the core lifecycle of catalyst analysis: discover top picks, drill into any ticker's signal, read a narrative thesis, assess sector direction, obtain options context for trade construction, and evaluate historical reliability. There are no obvious dead ends or missing operations for a read-only analytics use case.
