Run RSI + Bollinger Band mean-reversion strategy backtest.
`period`: history window, e.g. "1y","2y","5y","10y" (default "2y").
| Name | Required | Description | Default |
|---|---|---|---|
| period | No | 2y | |
| ticker | Yes | ||
| rsi_lower | No | ||
| rsi_upper | No |
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 disclose behavioral traits, but it only adds that `period` is a history window. It omits any mention of output format, data access, side effects, or operational constraints, leaving the agent without critical execution 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 extremely concise: two sentences with no filler. The structure front-loads the purpose and then details a key parameter, which is efficient, though it is too sparse to fully inform an agent.
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 4 parameters and no output schema, this description is a skeleton. It fails to describe return values, how RSI and Bollinger Band inputs interact, or common usage scenarios, making it incomplete for reliable tool invocation.
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 0%, so the description must compensate—it explains `period` with examples and a default but says nothing about `ticker`, `rsi_lower`, or `rsi_upper`. The RSI/Bollinger thresholds are left to inference from parameter names, which is insufficient.
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 action ('Run') and specific strategy ('RSI + Bollinger Band mean-reversion backtest'), which distinguishes it from sibling backtest tools like backtest_rsi_mean_reversion (RSI only) and backtest_macd_momentum. The resource (backtest) and scope are 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 gives no guidance on when to use this tool versus similar backtest strategies in the sibling set. It neither mentions alternative tools nor provides context like 'use this for ranging markets'—only an imperative statement.
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.
Several tools overlap significantly: plot_charts is an explicit alias for generate_charts, generate_chart_pack and generate_charts have similar purposes, and backtesting tools like backtest_macd_momentum vs backtest_macd_trend_follower or backtest_mean_reversion_rsi_bb vs backtest_rsi_mean_reversion are easily confused. The sector tools also have fuzzy boundaries.
Most tools follow a clear verb_noun pattern (analyze_*, backtest_*, get_*, generate_*). However, two tools use a 'tool' suffix (analyze_sector_intelligence_tool, find_sector_stock_pipeline_tool) which deviates from the otherwise consistent naming style.
At 25 tools, the server is at the heavy end of the acceptable range. The scope is broad (analysis, backtesting, charting, portfolio optimization, alerts), but redundant chart tools and overlapping backtest strategies inflate the count and hurt focus.
The toolset covers the core domain well: technical analysis, backtesting, trade planning, portfolio optimization, quotes, news, and alerts. Minor gaps exist, such as no watchlist management tool (scanning only) and no direct historical data fetch, but these are workable around the existing tools.