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

No annotations exist, so the description carries the full burden. It does disclose the data scope (only resolved markets are aggregated), the HTTP method, and the $0.05 x402 cost with a docs link, which is useful operational context. However it never states that this is a read-only aggregation, nor anything about latency, pagination, or freshness of the aggregates.

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 opening sentence front-loads the essence well, but the second sentence is long and repeats items already named ('how often the model beat the market (hit rate)' re-states hit rate, 'a model calibration curve' re-states calibration). The trailing bracket is dense but functional; overall it is moderately verbose rather than tight.

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?

With no output schema, the description does a fair job naming the returned aggregates (hit rate, edge captured, calibration curve, per-hazard breakdowns), which covers the return-value burden. But both input parameters are left unexplained, and nothing routes the agent away from the overlapping edge_calibration sibling, so the picture is incomplete for a two-param data 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?

Schema description coverage is 0%, so the description must compensate, and it largely does not: neither 'window' (required, default 90) nor 'min_divergence' is explained anywhere. Worse, it highlights 'model_label' as a meaningful selector even though model_label is absent from the input schema, which can mislead the agent about what it can pass in.

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 gives a concrete verb-of-effect (aggregates stored edge signals) and a precise resource (historical backtest performance of the edge signal), enumerating the outputs: hit rate, edge captured, calibration curve, per-hazard breakdowns. It is clear what the tool does, but it never distinguishes itself from the very similar sibling edge_calibration, which also deals with calibration.

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 statement and no mention of the obvious alternative edge_calibration. The agent is left to infer that this is for evaluating realized model performance from the phrase 'whose markets have resolved', but nothing states when this should be chosen over a sibling.

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