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

Annotations already declare readOnly, idempotent, non-destructive, so safety needs no restating. The description adds substantive domain context: the data is a historical accuracy audit comparing predictions to settlements. It doesn't mention freshness/coverage windows, but with an output schema present, much of the return detail is already structured.

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?

Three short sentences, front-loaded with what the metric is, followed by the return granularity and the usage cue. No filler or redundancy.

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?

A no-parameter read tool with annotations covering safety and an output schema covering the return shape. The description supplies the remaining conceptual context an agent needs: what 'track record' means here and why it matters.

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?

Zero parameters, so the baseline of 4 applies. There is nothing for the description to clarify beyond implicitly noting the results are unfiltered across all series and buckets.

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 resource (Sardine's published numbers scored against settlements) and a specific output shape (per series and probability bucket: predicted, settled, miss in points). This is clearly distinct from siblings like backtest_rule or get_settlement_rate, which measure different things.

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?

"Use this before relying on any number" gives a concrete trigger condition for invoking the tool. It does not name an alternative or state when not to use it, which keeps it short of a 5.

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