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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint: false, so the safety profile is covered. The description adds meaningful behavioral detail beyond that: the data is 'live,' hit rates are measured at 5m/15m/1h/24h, and it includes calibration buckets and latest signals with outcomes. It does not contradict the annotations.

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 definition is a single dense sentence with no filler and front-loads the core subject before adding scope and options. It is slightly run-on, but each clause contributes useful information and nothing needs to be removed.

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 read-only data retrieval tool, the description communicates the main output content and the optional symbol filter. However, it omits the meaning of the 'window' parameter, does not specify how 'days' is bounded or interpreted, and there is no output schema to compensate for the missing response structure, leaving invocation partially underspecified.

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?

With schema description coverage at only 33%, the description needed to compensate, but it only clearly maps to 'symbol' via 'optionally for one symbol'; 'days' is only vaguely hinted by 'over the last days.' The 'window' parameter is left unexplained, and the listed output horizons (5m, 15m, 1h, 24h) do not obviously map to the enum [1m, 5m, 15m], creating ambiguity for an agent choosing a valid value.

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 identifies a specific resource: the live track record of published signals, with hit rates at multiple horizons, calibration buckets, optional symbol scope, and latest outcomes. It goes well beyond the tool name and distinguishes the tool from generic market-data siblings, though it lacks an explicit verb like 'retrieve' and does not directly contrast with backtest_signals.

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 implies the use case by emphasizing 'published signals' and 'outcomes'—evaluating live signal performance—and notes the optional symbol filter. However, it gives no explicit when-to-use versus alternatives, such as preferring backtest_signals for hypothetical strategies or this tool for live performance monitoring.

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