Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It discloses detailed behavioral traits: no-look-ahead fills, costs, walk-forward split, Monte Carlo bands, overfit warnings, asset classes, time frames, payment requirements, and the 402 response for uncredentialed calls. Missing only are specifics about the output format or response structure, but the level of disclosure is high.

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 a single dense paragraph that front-loads the core purpose and then lists features, assets, cost, and payment flow. While packed with value, it could be more readable with bullet points or separation of fee info. Every sentence is earned, but the density slightly reduces clarity.

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 0 shown parameters, no output schema, and complex simulation behavior, the description covers usage domain, constraints, and payment model well. However, it lacks any description of what the tool returns (output format, success/error indicators), which is a notable gap for a complete context. The instruction to use the 'instruments' tool for parameters is helpful but partially shifts the burden.

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?

The input schema has 0 properties with additionalProperties (string) and directs to the 'instruments' tool for parameter docs. The description adds no information about actual parameters—neither names, types, nor purposes. Schema coverage is technically 100% (no fixed params), but the description fails to add meaning beyond the schema; it punts responsibility entirely.

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 does backtesting: 'plain-English trading rule compiled to an explicit spec and simulated honestly' across equities/FX/crypto and prediction markets. This specific verb+resource combination distinguishes it from all sibling tools (e.g., scan_*, signal_*, analysis) which focus on scanning, signals, or analysis rather than full historical simulation.

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?

Usage is implied: use for backtesting strategies. However, the description provides no explicit guidance on when to prefer this tool over alternatives like analysis or track_record. It mentions it is paid and directs users to the free 'instruments' tool for parameter docs, but does not specify when to choose backtest vs other tools for different tasks.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.