signal_outcomes

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

Annotations already declare readOnlyHint, idempotentHint and closed-world, so the safety profile is covered; the description goes beyond that by explaining what the numbers mean (excess return in percentage points over the same trading days as SPY) and warning that results are regime-scoped and can be thin. It never says what happens with an invalid/nonexistent score_version, which keeps it from a 5.

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 payload is front-loaded into the first sentence and the supporting detail follows in a logical order (what is snapshotted → what is returned → how to read it → regime caveat → args). It runs longer than strictly necessary and re-explains the SPY logic twice, so a sentence or two could be trimmed.

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 an output schema present, the description needn't enumerate return fields, and it instead supplies the interpretive context an agent needs: the 30/60/90-day horizon, SPY-relative framing, sample-size caveat, and version scoping. The only remaining gap is not stating what an out-of-range or unknown score_version yields.

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 coverage is 0% and the schema only offers a nullable integer with default null, so the description has to carry the meaning — and it does: the parameter restricts to one scoring regime and defaults to the current one. The only weakness is a mild mismatch with the schema's literal null default, leaving an agent to infer that null means 'current regime'.

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?

Opens with a concrete verb+resource question ('Does a label actually go up — and beat the market?') and then states exactly the artifact: per-label score-bucket outcomes at 30/60/90 days with resolved counts, up/down/flat, win rate, and excess return vs SPY. That is specific enough to separate it from siblings like ticker_signal, top_signals, or leaderboard, which do not report resolved forward returns.

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?

Gives explicit consumption guidance ('lead with the SPY numbers') and a reporting rule ('Small resolved counts mean the regime is young — say so'), plus the caveat that scoring regimes change over time. It does not name a sibling tool or state when to prefer one over the other, so it stops 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.