compute_correlation_regimes

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

With no annotations, the description carries the full burden of behavioral disclosure. It discloses a non-obvious behavior (missing bars are never forward-filled) and a scope limitation (closed bars must share exact UTC timestamps). It also frames the output as descriptive, which helps set expectations. It does not mention side effects or return format, but the core computational behavior is transparent.

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?

Three sentences, each earning its place: purpose, data alignment requirement, and interpretive caveat. The most important constraint is front-loaded immediately after the purpose, and there is no filler or redundant schema repetition.

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?

Given the tool's complexity (9 parameters, 5 required, no output schema, no annotations), this description is not sufficient for an agent to invoke it correctly. It omits what the output looks like, how thresholds map to regimes, and how the required symbol/timeframe fields should be populated. The description gives a solid high-level orientation but lacks critical operational detail.

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, but it only references two charts and timestamp alignment. It does not explain count, window, strong_threshold, neutral_threshold, or the expected symbol/timeframe parameters. An agent is left to guess how rolling window and thresholds affect the classification.

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 ('Classify') and a precise resource ('rolling return correlation between two explicitly bound layout charts'), making the tool's function immediately clear. It also introduces a defining constraint (exact UTC timestamp matching) that separates it from more generic correlation tools.

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 description gives clear contextual guidance: it works on two explicitly bound layout charts and requires exact timestamp alignment. It also gives a when-not-to-use signal by stating the output is descriptive evidence, not a trading signal, though it does not name specific alternative tools or explicit exclusions.

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