Pro Tier-1 gate: score >= 6/8, inside 9:45–3:45 PM ET window, level present.
Pass alert_json to check a specific record; else uses latest alert.
| Name | Required | Description | Default |
|---|---|---|---|
| alert_json | No | ||
| use_latest | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | 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?
No annotations are provided, so the description carries the full burden. It discloses exact scoring threshold, the ET trading window, the level requirement, and the fallback to latest alert when alert_json is omitted. It doesn't state read-only or error behavior, but 'check' implies a non-mutating operation and the presence of an output schema covers return shape.
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?
Two compact sentences front-load the core gate criteria before parameter behavior. No filler; every clause adds distinct information.
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 tool has only two optional parameters, an output schema exists, and the description supplies the key gate conditions plus param selection behavior. Slight ambiguity remains around what 'level present' means and where the score originates, but these are domain details rather than blocking gaps.
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?
With 0% schema description coverage, the description compensates by explaining alert_json's role (check a specific record) and the default latest-alert behavior. It doesn't explicitly name the use_latest parameter or specify the alert_json string format, but the relationship between the two parameters is clear enough for invocation.
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 establishes a clear evaluation role: a Tier-1 gate with explicit pass conditions (score >= 6/8, ET time window, level present). It is distinguishable from siblings like get_latest_alert because it is a gate/check rather than a retrieval. Minor omission: no explicit verb like 'checks whether', but the name and criteria make intent clear.
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 useful context: it is the Tier-1 gate, and it can operate on a specific alert_json or fall back to the latest alert. However, it doesn't name sibling alternatives or state when not to use this tool, so the agent must infer routing from sibling names.
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.
Each tool targets a distinct metric or workflow—alert checks, alert lists, gamma maps, volatility indices, replay timelines, execution plans—so an agent can reliably pick the right one from its description. Even the alert-related tools (get_latest_alert, list_alert_history, check_alert_tradeable) have clearly separate outputs.
All tool names follow a consistent verb_noun snake_case pattern (mostly get_, plus check_, format_, list_, plan_). This makes the set predictable and easy to scan.
At 32 tools, the surface is heavy and approaches a disorganized collection of endpoints rather than a curated set. Many individual get_* indicators could be grouped into a smaller number of dashboard or snapshot tools without losing clarity.
The server covers the core 0DTE intelligence lifecycle: alerts, historical replays, risk overlays, structure, gamma, volatility, news, and advisory planning. Minor gaps exist—such as a direct quote or option chain feed—but they are not essential to the stated purpose.