FREE. How often our own signals turned out right, scored against a naive baseline. Every claim is written down before the outcome exists and scored afterwards from our own recorded series. Read this before trusting any signal here — including to find out which ones we cannot yet justify charging for.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | window, default 30 |
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 provided, the description carries the full burden. It discloses the methodology ('Every claim is written down before the outcome exists and scored afterwards from our own recorded series'), the cost ('FREE'), and the tool's role in signal trust assessment. It does not mention rate limits or return format, but the behavioral context is sufficient for an agent.
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 three sentences, each earning its place: purpose, methodology, and usage guidance. It is front-loaded with the core purpose and contains zero wasted words.
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 tool with one optional parameter, no output schema, and no annotations, the description covers the concept, methodology, and usage intent. It does not detail the return format, but the agent can infer calibration metrics are returned. The description is complete enough for selection and 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 100% (the single 'days' parameter has a description: 'window, default 30'). The tool description adds no additional meaning about the parameter, so it scores at the baseline. The parameter is adequately documented in the schema.
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 purpose: 'How often our own signals turned right, scored against a naive baseline.' It uses a specific verb+resource and distinguishes from sibling tools like get_signal_history_7d (historical data) and get_funding_predictions (predictions) by focusing on calibration accuracy.
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 provides explicit guidance: 'Read this before trusting any signal here — including to find out which ones we cannot yet justify charging for.' This tells the agent when to use the tool (before other signals) and implies its role in evaluating trustworthiness. However, it does not explicitly name alternatives or state when not to use it.
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.
Most tools target clearly distinct metrics, but the paid/free sample pairs (get_crypto_prices/try_crypto_prices, etc.) and overlapping summary tools (get_market_overview, get_market_pulse, get_overnight_risk_brief) create some selection ambiguity. Descriptions list components, so an agent can disambiguate with effort, but the boundaries between bundles and single-purpose tools are not always obvious.
Tool names consistently follow a verb_noun pattern: get_ for data retrieval, try_ for free samples, and watch_condition for persistent monitoring. All names use lowercase snake_case with no mixed conventions, making the naming predictable and easy to navigate.
34 tools is well above the comfortable range for a typical MCP server and feels heavy even for a broad crypto data domain. The count is inflated by paid/free sample duplicates and multiple bundle variants that could have been consolidated.
The surface covers a wide range of crypto data: prices, funding, sentiment, arbitrage, derivatives, on-chain metrics, signal history, and monitoring. Minor gaps exist—such as no obvious generic signal discovery tool or order-book/trade-level data—but the core domain of market data with checkable records is thoroughly served.
