get_history[Market data: crypto] Rolling 90-day band-dot backtest with forward moves and live hit rates (green dots carry the edge; red near coin-flip). Paid: $0.05 USDC on Base, paid in-band via x402 MCP (@x402/mcp; _meta "x402/payment"). Also at GET https://micro-saas-agent.onrender.com/api/history.
| Name | Required | Description | Default |
|---|---|---|---|
| pair | No | ||
| pass | No | Optional GW8 day pass token (from buy_day_pass / POST /api/pass/day); skips per-call payment |
Changes observed during successful MCP inspections.
Input schema / properties / passAdded value: +{
+ "description": "Optional GW8 day pass token (from buy_day_pass / POST /api/pass/day); skips per-call payment",
+ "maxLength": 80,
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description does real work: it discloses the $0.05 USDC on Base price, the x402 in-band payment flow and _meta key, and how to interpret output (green dots carry the edge, red is near coin-flip). It omits error/auth failure behavior and the response shape, but the cost and interpretation disclosure is well beyond a bare call description.
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?
A single dense sentence plus a domain tag, front-loaded with purpose and followed by interpretation, price, and alternate endpoint. Each clause carries information, though the cramped abbreviation style ('paid in-band', '_meta') slightly hurts scanability.
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 two-parameter, no-output-schema tool, the description covers purpose, interpretation, and payment prerequisites. It still leaves the return structure and the distinction from get_band_dots unstated, which an agent needs to choose correctly between the two.
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 coverage is 50%: the pair parameter is fully documented by its large enum, and pass carries its own schema description. The tool description adds no meaning about pair selection or what a band-dot represents per pair, so it neither compensates for the gap nor needs to compensate much.
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?
States a specific verb and resource: a rolling 90-day band-dot backtest with forward moves and live hit rates, plus the crypto domain. However, it never differentiates itself from the sibling get_band_dots, which an agent could plausibly confuse with this history/backtest tool.
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?
There is no explicit when-to-use guidance or exclusion relative to get_band_dots, get_sample, or other signal tools. The only routing information is an alternate access path (GET URL), which addresses transport, not tool selection.
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.