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

The annotation already covers read-only safety, and the parameter documentation adds useful behavioral context: filtered results carry `universe` and `alertsOutsideUniverse`, every metric is computed on that market alone, indeterminate-market alerts are excluded, and unfiltered averages mix two source coverage regimes. This gives the agent far more than the bare readOnlyHint would alone.

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 actual description is a single tight Polish sentence that front-loads the tool's evaluative purpose. Longer rationale lives in the parameter schema where it belongs, and nothing in the description is redundant or padded.

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 simple read-only query, the important constraints are well covered: annotations declare safety, all parameters are documented, and the `universe` rationale explains scope-dependent behavior. The only meaningful gap is that no output schema exists and the description does not precisely specify the return shape beyond the general notion of how many alerts 'proved correct.'

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 100%, so the baseline is 3; the schema already documents defaults, max lookback, deprecation, uniqueness constraints, and the universe enum semantics. The tool description itself adds no parameter-level detail beyond what the schema provides.

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 Polish description states a clear verb+resource: it evaluates the alerts the user received and how many turned out correct, so the core purpose is understandable. It does not explicitly distinguish itself from siblings like get_alert_delivery_stats or historical_event_hit_rate, so an agent has to infer the difference from the personal 'które dostałeś' phrasing.

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 main description gives no explicit when-to-use guidance or named alternatives, but the `universe` parameter documentation supplies strong context: it explains when filtering by market matters shouldn't be skipped and why unfiltered hit rates can be misleading across two very different data sources. There are no exclusions, but the scoping guidance is clear enough to guide correct usage.

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