perps_market_trendPer-symbol (SOL/BTC/ETH) deltas for mark price, total open interest, long/short skew, utilization, and borrow APR over 7/14/30 days. Direction indicators per metric and per market. Overall direction excludes mark price. Use for regime detection — bots that adjust behavior based on whether markets are growing, stressed, or rebalancing.
| Name | Required | Description | Default |
|---|---|---|---|
| lookback | No | History window | 7d |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses the computation (deltas, direction indicators), the exclusion of mark price from overall direction, and the available lookback periods. It does not explicitly state it is read-only or mention data availability limitations, but the context is sufficient for a data analysis tool.
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 long and front-loaded with the key output metrics and lookbacks. The second sentence adds direction indicators and the intended use case. No filler or repetition.
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 tool with one parameter and no output schema, the description explains what metrics are returned, how direction is interpreted, and the intended use case. It lacks an explicit statement about the output structure or how to distinguish from perps_market_structure, but it is complete enough for an agent to select and invoke 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?
The only parameter (lookback) has 100% schema coverage with a clear description ('History window') and enum values. The tool description mentions 'over 7/14/30 days' which aligns with the schema but adds little beyond it. Baseline 3 is appropriate since the schema already provides full semantics.
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 specifies the resource (Perps market trend for SOL/BTC/ETH), the metric deltas (mark price, OI, skew, utilization, borrow APR), and the lookbacks (7/14/30 days). It also states the output includes direction indicators and overall direction, making it distinct from sibling perps tools like perps_market_structure or perps_basis_signal.
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 use case: 'Use for regime detection — bots that adjust behavior based on whether markets are growing, stressed, or rebalancing.' This clearly tells an agent when to invoke the tool, though it does not explicitly exclude alternatives or compare with 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.
With 32 tools, several have overlapping purposes, such as wallet_history vs portfolio_history (both track wallet portfolio over time) and smart_money_flow vs smart_money_trenches (both follow smart money movements). However, most tools have clearly distinct scopes, and detailed descriptions help differentiate them.
All tool names follow snake_case with a predictable verb_noun or noun phrase pattern (e.g., enrich_token, compare_wallets, perps_market_trend). The consistent structure makes the set easy to navigate, even the 'perps_' prefix group is uniform.
32 tools is well above the 25-tool threshold, making the surface feel heavy. While the breadth reflects the wide domain of Solana analytics, the sheer number can overwhelm agents and increase the chance of selecting the wrong tool.
The tool set covers most aspects of Solana token/wallet/perp analysis, including enrichment, comparison, trend tracking, smart money flows, and perp market structure. Minor gaps exist, such as no direct historical OHLCV endpoint, but the existing tools handle core workflows well.