The raw 32-D regime-aware factor-state embedding vector for a ticker — the representation the similarity search itself runs on. Build your own models / similarity on it. QUANT tier only.
| Name | Required | Description | Default |
|---|---|---|---|
| ticker | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| dim | No | Vector dimensionality (currently 32). | |
| as_of | No | ||
| ticker | Yes | ||
| embedding | Yes | The raw factor-state embedding. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds meaningful context beyond that: the embedding's dimensionality (32-D), its regime-aware factor-state nature, and that it powers the similarity search. It also discloses the QUANT tier restriction, which is a form of access/authorization 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 two sentences with no redundant wording. The first sentence front-loads the core output and its nature, while the second explains usage and access tier. Every word earns its place.
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 that the tool has a simple read-only operation with a single parameter and an output schema exists, the description covers the essential context: what the vector is, how it relates to similarity search, and who can use it. It does not mention rate limits or error handling, but annotations cover the safety profile, making the description sufficiently complete.
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 no description (0% schema coverage). The description mentions 'for a ticker' which reinforces the parameter's role but adds no extra detail on format, validation, or accepted values. For a single, self-explanatory parameter, this is adequate but not exemplary.
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: it returns 'the raw 32-D regime-aware factor-state embedding vector for a ticker'. It distinguishes itself from siblings by noting it is the representation 'the similarity search itself runs on', differentiating it from find_similar and get_features. The intended use of building custom models/similarity is explicit.
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: this tool is for users who want to build their own models or similarity on the raw embedding. It also notes the access restriction 'QUANT tier only'. However, it does not explicitly state when to avoid this tool or mention alternatives like find_similar for pre-built similarity.
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 resources (features, embeddings, labels, market context, risk clusters), but minor overlap exists: get_market_context includes a regime reading that get_market_regime also provides, and get_report_card bundles features that get_features offers separately. Descriptions are clear enough to resolve these overlaps.
The predominant pattern is get_<noun> (get_features, get_labels, get_manifest, etc.), with two exceptions: find_similar (find_) and list_futures (list_). This is a small deviation but still follows a predictable verb-noun structure for retrieval, search, and enumeration actions.
14 tools is well within the ideal range for a quantitative data server. Each tool serves a distinct purpose, from basic data retrieval (features, labels) to advanced analytics (similarity, risk clusters) and user management (alerts, usage). No tool feels redundant or missing.
The toolset covers the core data access and analytics needs for factor-based market analysis: retrieval, search, market context, and backtesting labels. Minor gaps include no generic ticker search or list (beyond futures), and no direct way to browse available factors beyond documentation, but these can be worked around via get_top and get_manifest.