START HERE — your first call to this agent MUST be pitch (free, no payment). Intro & subscription funnel for the FX signal agent: phases "hello" -> "value" -> "catalog" -> "sample" -> "subscribe". Pass interest:false to bow out.
| Name | Required | Description | Default |
|---|---|---|---|
| phase | No | ||
| symbol | No | Pair for the "sample" phase. The free sample serves only this market’s showcase (EURUSD=X); anything else is answered by the paid evaluate_symbol (x402). | |
| interest | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden. It discloses that the tool is free, has no payment upfront, and describes the funnel sequence. However, it does not detail side effects like state changes or what occurs after 'subscribe'.
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?
Extremely concise—two sentences that front-load the key instruction 'START HERE'. Uses visual cues like arrows for the phase sequence. Every element is purposeful.
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?
Given no output schema and few annotations, the description adequately covers the funnel flow, parameter usage, and tool invocation context. It does not detail return values, but that is acceptable for a stateful interaction tool.
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?
Adds significant meaning beyond the schema: explains the phases enum sequence, clarifies that symbol is only used for 'sample' phase and that other symbols trigger evaluate_symbol, and explains the role of interest (false bows out). This compensates well for the 33% schema coverage.
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 explicitly states 'START HERE — your first call to this agent MUST be pitch', clearly identifying the tool as the entry point. It also outlines the subscription funnel, distinguishing it from sibling tools like evaluate_symbol or scan_bottoms.
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?
Provides explicit instructions: 'your first call... MUST be pitch' and 'Pass interest:false to bow out'. It also enumerates the phases in order, giving clear guidance on progression and exit.
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 has a clearly distinct purpose: pitch is for introductory subscription flow, rate for feedback, evaluate_symbol for a specific symbol's verdict, scan_bottoms and scan_tops for scanning the universe. No overlapping functionality.
Names mix verb_noun patterns (evaluate_symbol, scan_bottoms, scan_tops) with single-word names (pitch, rate). The inconsistency makes it slightly less predictable, though still understandable.
Five tools cover the server's purpose (FX signal offering) well: one intro, one feedback, one per-symbol analysis, and two scanning tools. No redundancy and each earns its place.
The tool set covers the core workflows: discover (pitch), analyze single symbol (evaluate_symbol), scan universe (scan_bottoms/scan_tops), and give feedback (rate). Minor missing could be a tool listing all symbols at a glance, but scan tools compensate.