get_prediction_market_yieldsNear-certain Polymarket outcomes ranked by annualized return to resolution — the "cash-like yield" view of prediction markets.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum rows to return (1-25). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering safety and idempotency. The description adds conceptual context about the ranking metric (annualized return) and the 'near-certain' filter, which provides some behavioral insight beyond annotations, though it does not explain pagination or output format.
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, well-structured sentence that front-loads the main concept and uses a clarifying dash to explain the 'cash-like yield view'. Every word contributes value, with 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 list tool with one optional parameter, the description sufficiently explains what data is returned and how it is ordered. The lack of an output schema is mitigated by the clear description, though it stops short of specifying exact fields or threshold definitions for 'near-certain'.
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 input schema fully describes the single 'limit' parameter with a default and range, so schema coverage is 100%. The description does not add parameter-specific details, but the baseline of 3 applies because the schema carries the semantic weight.
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 states the tool retrieves near-certain Polymarket outcomes ranked by annualized return to resolution, which clearly indicates its function. It differentiates itself from siblings like get_prediction_market_catalysts by framing it as the 'cash-like yield view', though it lacks an explicit verb like 'list' or 'get'.
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?
Usage is implied through the 'cash-like yield view' framing, suggesting it is appropriate when exploring safe, fixed-income-like opportunities in prediction markets. However, no explicit when-to-use or alternative tools are mentioned, so it relies on the user inferring the context.
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.
With 40 tools, many share overlapping domains: get_smart_money_flow vs get_smart_money_inflow, scan_launchpads vs get_launchpad_radar, track_whales vs get_hyperliquid_whales, and check_token_safety vs analyze_token_security. The detailed descriptions help, but the boundaries are not always clear, making misselection likely.
The tool names employ a wide variety of verbs (get_, analyze_, scan_, track_, find_, generate_, recommend_, run_, list_, ask_, assess_, detect_) with no consistent pattern. While all use snake_case, the inconsistent verb choices and occasional deviations like forecast_chart prevent predictability.
40 tools is well above the typical 3-15 well-scoped range and exceeds the 25+ threshold for 'too many'. While the broad 'crypto intelligence' purpose justifies some breadth, the sheer number makes the surface unwieldy and suggests a lack of focused scoping.
The tool set covers a wide range of crypto intelligence domains: market analysis, forecasting, whale tracking, yield/arbitrage, security checks, prediction markets, backtesting, and even content generation. Missing operations are minor (e.g., no direct portfolio management), but core analysis and data retrieval workflows are well represented.