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

Beyond the readOnlyHint and openWorldHint annotations, the description discloses crucial behavioral details: aggregation across all assets, the denominator contract (total counts unsettled signals), win_rate null semantics, and the distinction between partial and full take-profit. These are non-obvious and critical for correct usage.

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?

Although the description is lengthy, every sentence adds unique value: the scope, the data source, the denominator contract, the win_rate null handling, and the pointer to get_proof. It is densely packed but well-organized, with no filler.

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 the complexity of the performance metrics and the presence of an output schema, the description goes beyond what structured data provides. It explains key output fields and their semantics, and covers edge cases (null win_rate, unsettled signals), making the tool fully comprehensible for an agent.

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 only lists 'days' with a default and type, but the description adds the valid range (1-365) and default (30). Since schema description coverage is 0%, this compensation is essential and fully addresses the parameter's meaning.

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 function: 'Backtest performance over last N days' and specifies the data source ('Same data as REST /performance'). It distinguishes from siblings by explicitly mentioning 'no asset filter' and pointing to get_proof as an alternative for a different use case.

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 usage guidance: it explains when to use this tool (for aggregated performance over a date range) and when not to (for per-type verdicts, use get_proof instead). It also warns about the denominator contract, which is essential for correct interpretation.

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