Backtest the funding-harvest strategy (S2) on our REAL funding archive: gross/net %, annualized, winrate, max consecutive negative periods, verdict. Params: exchangeA, exchangeB, symbol, days (max 90), sizeUsd.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | ||
| symbol | Yes | ||
| sizeUsd | No | ||
| exchangeA | Yes | ||
| exchangeB | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must carry behavioral transparency. It lists outputs but provides no information about side effects, permissions, read-only status, rate limits, or error behavior. The only behavioral hint is that it uses 'REAL funding archive', which is not sufficient for a clear understanding of the tool's side effects.
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 concise, consisting of one purpose sentence and a parameter list. It front-loads the main function and does not waste words, making it easy to parse.
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?
The description covers purpose and outputs, but lacks essential context such as parameter semantics, error handling, output format, and any prerequisites or side effects. Given the absence of annotations, this is insufficient for an agent to fully understand how to use the tool reliably.
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 description lists the parameter names ('exchangeA, exchangeB, symbol, days (max 90), sizeUsd') but does not explain their roles. It provides a constraint for 'days' (max 90) but leaves the meaning of exchangeA/exchangeB, symbol, and sizeUsd undefined. Since the schema has no parameter descriptions, the tool description only partially compensates.
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 the tool's function with a specific verb ('Backtest'), the resource ('funding-harvest strategy S2 on our REAL funding archive'), and the expected outputs ('gross/net %, annualized, winrate, max consecutive negative periods, verdict'). This distinguishes it from sibling tools that fetch data or signals.
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 implies that this tool is for backtesting, but it does not explicitly state when to use it over alternatives (e.g., get_funding_rates, get_basis_history) or provide exclusions. Usage must be inferred from the purpose, which is clear but not explicitly contrasted with other tools.
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.
Many tools serve distinct purposes (hedging, funding, agents, market data), but several overlap heavily: get_basis_regime, get_basis_signal, get_basis_history, analyze_pair_liquidity, and get_perp_arbitrage all analyze exchange spreads/basis with blurred boundaries. Similarly, close_hedged_position vs close_position and hedge_status vs list_hedge_positions vs get_positions could cause misselection without careful reading.
The set predominantly follows a verb_noun pattern (get_*, open_*, close_*, set_*, list_*, place_*) which is predictable and readable. Minor deviations exist: agent_chat, agent_trigger, and square_post break the convention, and the hedge-specific tools mix status/list/adjust naming inconsistently.
35 tools is on the heavy side and pushes past the ideal scope for a single server. Many tools are data-retrieval variants (basis history/regime/signal/liquidity) that could be consolidated, and the breadth from news to square posts to agent management makes the surface feel sprawling rather than focused.
Core workflows (hedging, basis analysis, funding arbitrage, agent interaction, position management) are well covered, but there are noticeable gaps: there is no cancel_order tool despite get_open_orders and place_order existing, no order history or trade history, and no exchange-side position listing for real user positions. The server covers its niche but leaves some common trading dead ends.