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

Annotations already declare readOnlyHint=true, and the description adds value beyond that: the emphatic 'A historical base rate, NOT a forecast' caveat and the 'context, never a promise' warning are genuine behavioral disclosures that prevent misuse. It also exposes what the return contains (n, median, 10th–90th percentile). Minor gap: it doesn't define how 'similar setup' is computed or address small-sample reliability.

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?

Two compact paragraphs with the core purpose front-loaded and the critical forecast disclaimer separated out. Slight redundancy ('historical base rate' appears twice, and 'context, never a promise' restates the NOT-a-forecast point), but no wasted or filler sentences.

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?

The description covers what the tool computes, what it returns, how the horizon parameter behaves, and how it relates to get_thesis — and an output schema exists to carry return-format details, so those need no elaboration. The only substantive omission is entity input format, which slightly undercuts completeness for a tool with sparse schema descriptions.

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 0%, so the description must compensate. It does well for `horizon`, defining it precisely as 'the trading-day window to headline (1, 3, 5, or 10)'. However, `entity` is only implied as 'a stock' via context — its format (ticker vs. resolved name) is never stated, and the presence of a resolve_entity sibling suggests this matters. Partial compensation, with one clear gap.

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 verb and resource: 'Returns the forward-return distribution' for a 'stock's CURRENT chart setup' structured as a historical base rate. The framing as pattern intelligence read 'BESIDE the fundamental thesis, not instead of it' explicitly distinguishes it from fundamental-analysis siblings like get_thesis.

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?

Explicitly names get_thesis and prescribes the pairing: 'does the chart's usual outcome agree with the fundamental case?' The 'not instead of it' language is a clear when-not boundary, and the forecast disclaimer tells the agent what the tool can and cannot be used for.

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