Behavior correlations

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

Annotations declare readOnlyHint true, so no mutation concerns. The description adds behavioral context: day-to-day analysis, Pearson r, strength labels, plain-English interpretations. No contradictions.

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 a single paragraph that front-loads the main purpose and lists correlations. It is concise with no extraneous words. Could be structured with bullet points for readability, but not necessary.

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 existence of an output schema (not shown), the description does not need to detail return format. It provides enough context on the nature of correlations and interpretation. The missing parameter link reduces completeness slightly.

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?

The only parameter 'days' has default 90 and no schema description (0% coverage). The description mentions '7-180 day window' but does not explicitly state that the parameter controls the window length. This is a gap for a single-parameter tool.

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 clearly states the tool computes how user metrics move together day-to-day over a 7-180 day window. It lists specific correlations (strain vs recovery, etc.) and distinguishes from sibling trend tools like get_recovery_trends which show individual trends, not relationships.

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 the time window and includes a caution ('correlation, not causation'). It implies usage for understanding pairwise relationships between metrics, but does not explicitly contrast with sibling tools. Slightly improved by stating when to use alternatives like get_recovery_trends.

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