compute_correlations

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

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds context beyond annotations by specifying the data source ('daily returns over a window'), input constraints ('2-20 tickers'), and return contents ('the matrix, per-asset annualized vol, and the top-correlated pairs'). This is meaningful but could be richer on edge cases or missing data handling; a 4 is appropriate.

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, every one earning its place. The purpose is front-loaded, followed by input constraints, output summary, and a comparative note. No fluff or repetition of annotations.

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 only 2 parameters, an output schema, and read-only annotations, the description fully covers what the tool does, its inputs, its outputs, and when to prefer it. Nothing essential is omitted, especially given the output schema supplies formal return details.

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 100%, so the schema fully documents both parameters. The description repeats parameter constraints ('2-20 tickers', timeframe default '1Y') without adding new semantic meaning. It does mention the output concept, but that's not parameter semantics. Baseline 3 is correct.

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 verb+resource: 'Pairwise correlation matrix + annualized volatility from daily returns over a window.' It clearly distinguishes from siblings by noting it's 'Lighter than analyze_quantitative when you just want raw pairwise structure without a factor model,' and it also differs from compute_betas/compute_returns by explicitly covering correlation and volatility.

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?

Explicit guidance is provided: 'Lighter than analyze_quantitative when you just want raw pairwise structure without a factor model' names an alternative and specifies the condition for choosing this tool. This directly tells when to use it instead of a heavier factor-model tool, satisfying the criterion for explicit alternatives.

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