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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and non-destructive, so the safety profile is covered. The description adds value beyond that: per-call cost ($0.05) and the crucial epistemic caveat that the output is observation, not probability. It does not disclose rate limits or whether the optional context sources can fail independently.

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?

Tight and front-loaded: capability first, then the caveat, then cost, then return fields. The final 'Returns: symbol, as_of, source, context…' sentence is largely redundant given an output schema exists, and that space would have been better spent on `history`.

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 tool with 6 parameters, a nested object carrying a strict 21-item minimum observation array, and open-world external sources, the description leaves the agent without enough to construct a valid call. The output schema does relieve it of explaining return values, but the `history` precondition and the behavior of each context flag are the most important gaps and neither is addressed.

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 17% across 6 parameters, so the description must compensate and largely does not. It mentions the context sources (news, SEC, Polymarket, economic) which maps to one param, but says nothing about the complex nested `history` object (21–2000 observations, adjusted closes), `fred_series`, `horizon_days`, or `language`. The heaviest, most error-prone parameter is entirely undocumented in prose.

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+resource: observed equity momentum and volatility for a symbol, with optional sourced context. The line 'Not a probability forecast' distinguishes it from forecast/prediction siblings such as hubvibe_market_forecast and hubvibe_market_prediction. It stops short of naming a specific alternative, but the negation does real differentiating work.

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 negative framing ('not a probability forecast') implies when to prefer it over forecast tools, and the mention of optional news/SEC/Polymarket/economic context hints at enrichment use cases. However, there is no explicit 'use this when…' statement, no prerequisite conditions, and it never routes the agent to or away from a named sibling. Usage is implied, not stated.

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