Stock-symbol vectors: which listed symbols an event, theme or headline moves, ranked in one call.
Scored across 1 tool
Only one tool exists, so there is no possibility of confusing it with another. Its scope (stock symbol and text embeddings) is clearly stated.
A single tool name, 'stock_vectors', is descriptive and self-consistent. There is no mixed convention to evaluate against.
A one-tool server is thin for a domain described as having multiple use cases (symbol vectors, text vectors, ranked similarity baskets, batch ranking). The count is defensible for a focused embedding endpoint but leaves no room for complementary operations.
The single tool covers embedding and pairwise ranking, but there is no way to inspect vector dimensions/space, list supported symbols, or persist results beyond a single call. Agents hitting a 64-input limit or needing metadata have no fallback.
Tuatara Embed Stocks: vector embeddings of listed stock symbols and of text in one space, built for the connections a sector label does not carry — which symbols an event, theme or headline moves, including companies it never names. Send sym:TICKER (e.g. sym:AAPL) for a symbol's own vector, or any text (a headline, a theme). With similarity_to_first=true the answer ranks inputs 2..n by cosine to input 1, so 'headline + candidate symbols in, ranked basket out' is one call. 4,096 dimensions, unit length. Up to 64 inputs per call; no account needed; nothing is stored.
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | list of texts to embed: sym:TICKER for a listed symbol's own vector, anything else is embedded as text; at most 64 | |
| encoding_format | No | base64 (default, float32 little-endian) or float (4,096 numbers) | |
| similarity_to_first | No | also return every other input's cosine to the first input, ranked (e.g. first = the headline, the rest = candidate symbols) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so safety is covered. The description adds substantive context beyond that: 4,096 dimensions, unit length, a 64-input cap, no account required, and nothing stored. These are operationally useful traits an agent would not infer from the annotations alone.
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?
Front-loads the resource and purpose, then moves to invocation modes and behavioral facts. The sentences are dense and slightly long, but nearly every clause carries useful information. Minor trimming possible without loss.
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?
No output schema exists, so the description must explain returns; it does so with dimensionality, unit length, and the ranked similarity behavior. The encoding_format return shapes live in the schema. Complete enough for correct invocation, though output structure could be stated more explicitly.
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%, so all three parameters are already documented in the schema. The description reinforces the sym:TICKER convention and frames similarity_to_first as a ranked-basket operation, but adds little syntax or constraint detail beyond what the schema already states. 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?
States a specific resource and operation: vector embeddings of listed stock symbols and arbitrary text in one shared space, with the distinct use case of capturing connections a sector label misses. An agent can tell exactly what this tool produces and why it differs from ordinary text embedding.
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?
Gives clear invocation patterns: send sym:TICKER for a symbol's own vector, or any text, and use similarity_to_first=true to rank inputs 2..n against input 1. The 'headline + candidate symbols in, ranked basket out' example shows the intended workflow. No explicit when-not-to-use guidance, but there are no siblings to route between.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
stock_vectorsExplainable model signals, drivers, news sentiment, SEC filings and macro data for US stocks.
Plain-English market screens over live US, India, ETF, forex and crypto data. Returns symbols.
Analytical engine for US-listed equities: screens, rankings, and event studies in plain English.
Percentile fingerprints, curated peers, theme clusters & market-stress context for US stocks.
Add one secure layer between your agents and this server.
