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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered; the description adds genuinely useful interpretation rules beyond that — what positive vs. negative z means, the three direction states including 'holding below two standard deviations', and the nine-week half-life weighting. It stops short of mentioning ordering guarantees at the result level or pagination beyond limit, 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 purpose is front-loaded and virtually no word is filler, but the entire definition is one long semicolon-chained sentence that mixes return-field definitions with parameter documentation. The parameter list is hard to scan and would benefit from being broken out.

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, return values need not be explained, yet the description still supplies the interpretive meaning of the fields (z direction, half-life weighting), and all five optional parameters are documented with defaults and constraints. Annotations cover the safety profile, so nothing an agent needs in order to call this correctly is missing.

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 has to carry the full burden and does: week accepts any date within the target week (with default), breaking_only is a two-standard-deviation threshold filter, family narrows to one family, market filters to pairs naming a given market with concrete examples (Gold, S&P 500, Bitcoin), and limit is bounded 1-200. Only 'family' lacks an example value, a minor 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?

The description names a concrete resource and scope — the pairs of one week of the Antevo Tremor Index, most unusual first — and enumerates what each pair contains (markets, family, weighted correlation, z-score, direction, 26/52-week correlations). That granularity implicitly separates it from siblings like get_tremor_index or get_tremor_breaks, but it never explicitly contrasts itself with them.

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 implied through parameter behavior: 'breaking_only (default true) keeps pairs at two standard deviations or more' and 'week is any date ... default the latest' tell an agent how the default call behaves. There is, however, no explicit guidance on when to reach for this tool over get_tremor_index, get_tremor_history, or get_tremor_breaks, and no stated exclusions.

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