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

The readOnlyHint annotation already establishes the safety profile, and the description goes beyond it by disclosing the substantive shape of the result: hit rate, top-10 vs bottom-10 spread, and benchmarking against QQQ, broken down by horizon. With no output schema present, this return-value disclosure is doing real work. It stops short of stating the lookback window or the set of horizons, which are the remaining behavioral unknowns.

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?

A single sentence, front-loaded with the core action and then unpacked into the three concrete metrics. Every clause adds information; nothing is padding.

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 zero-parameter, read-only tool with no output schema, the description covers what the agent most needs: what the tool returns and how it is segmented. The gaps are modest but real: no lookback period, no enumeration of which horizons exist, and no hint of result size or format.

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 tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The phrase 'per horizon' is worth noting: it reads as a dimension of the returned breakdown rather than a caller-supplied filter, which is consistent with the empty schema.

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 uses a specific verb ('Get') for a specific resource (historical performance of past QSignals scores) and enumerates the exact metrics returned: hit rate, top-10 vs bottom-10 average return, and performance vs QQQ. It implicitly separates itself from siblings like get_stock_score and get_top_picks (current/forward-looking picks vs retrospective performance), though it never names an alternative explicitly.

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?

Usage is only implied: 'past ... performed' signals this is the backtest/evaluation tool rather than a live-picks tool, so an agent can infer when to reach for it. There is no explicit when-to-use statement, no exclusion, and no mention of the sibling tools (get_all_scores, get_top_picks) that an agent might confuse it with.

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