theme_clusterThe statistical theme a stock actually trades with: clusters built from years of price co-movement (market-removed residuals → random-matrix cleaning → Ward linkage), not sector labels. Returns the cluster's name, description, cohesion, sector mix and up to 20 member tickers. Different question from peers (business competition) — this is who it MOVES with.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark this as read-only and non-destructive. The description goes beyond annotations by explaining the statistical methodology (market-removed residuals, random-matrix cleaning, Ward linkage) and the output limits (up to 20 member tickers). No contradiction with annotations; it adds substantive behavioral context.
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 brief and front-loaded with the core definition. Three sentences each add value: the concept, the return contents, and the differentiation from peers. No filler or redundant 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?
Despite lacking an output schema, the description enumerates what the tool returns: cluster name, description, cohesion, sector mix, and up to 20 member tickers. For a read-only single-parameter tool, this is complete enough for an agent to understand what the call will produce and how to use it.
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?
The schema has one parameter, `ticker`, with zero description coverage. The description compensates by indicating the input is a stock identifier ('a stock actually trades with') and that the output corresponds to that ticker. Though it doesn't specify format or casing, the single self-explanatory parameter name plus the context is sufficient for correct invocation.
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 what the tool does: returns the statistical theme a stock trades with, based on price co-movement clusters. It specifies the output contents (name, description, cohesion, sector mix, member tickers) and explicitly contrasts with sector labels and the `peers` tool, making its purpose unambiguous.
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 gives an explicit alternative (`peers`), explains the difference (business competition vs. co-movement), and provides a when-not context ('not sector labels'). This is exactly the explicit routing guidance that helps an agent choose this tool over its siblings.
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 owns a distinct analytical niche: single-stock character, multi-ticker comparison, market regime, business peers, co-movement cluster, and universe screening. The only near-overlap (fingerprint's peer list vs peers) is explicitly resolved by describing peers as the deeper standalone lookup.
All names are lowercase and stylistically consistent, but there is no verb_noun pattern: compare and screen are verbs while market_regime, peers, and theme_cluster are noun phrases. The mixed grammar is readable but not a strongly predictable naming convention.
Six tools is tightly scoped for a stock-character research server; each tool covers a distinct user workflow and none feels redundant. The count is well within the ideal range and does not burden an agent with overlapping endpoints.
The set covers the full intended workflow: assess market context, inspect a single stock, compare tickers, identify true peers and co-movement groups, and screen the universe on every available metric. There are no obvious dead ends or missing operations for a read-only analytics domain.