Correlation

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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses critical behaviors: candle series are joined by startedAt so only same-timestamp candles pair, tickers are validated, and an error is returned for insufficient or constant data. This is exactly the behavioral nuance that annotations alone cannot convey.

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 description is informative without being bloated, covering output semantics, matching behavior, validation, error handling, and an example. It is slightly dense due to multiple parenthetical clarifications, but each sentence adds substantive value.

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 statistical tool with an output schema, the description covers the main operational aspects: what is computed, how candle histories align, validation requirements, and failure conditions. The only notable gap is the undocumented limit and resolution parameters, but the rest of the context is strong.

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?

With schema_description_coverage at 0%, the description must compensate. It explains ticker_a and ticker_b through the example and format hint, but it says nothing about limit or resolution beyond the raw schema defaults. Two of the four parameters receive no semantic explanation.

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 states a specific statistical operation (Pearson correlation of log returns) and the resource (two markets' candles), and names the exact outputs: correlation r and beta. This clearly distinguishes it from siblings like market_ta or candles by defining a unique analytical purpose.

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 context for use: comparing two markets' log-return sensitivity, and explicitly instructs the agent to call list_markets for valid tickers in 'ETH-USD' format. It does not explicitly name when-not alternatives, but the usage context is strong enough for an agent to select it appropriately.

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