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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the analytic behavior: entangled candidates with VIF > 5 or |r| > 0.8 are flagged not_separable rather than ranked with 'a confident wrong number', and the 2-15 candidate bound is stated. It does not mention cost, rate limits, or runtime for large scans, but the core computational behavior is unusually well disclosed.

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?

Front-loads the core concept in the first clause and every sentence carries information (method, flagging rule, return fields, when-to-use, data sources, limits). It is long for a tool description and the 'weather vs promo' illustration is decorative, but nothing is padded.

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 no output schema, the description enumerates the return payload per candidate (standardized coefficient, raw slope, p-value, VIF, pairwise r, best lead/lag), plus input limits and supported data sources. For a statistically complex tool, an agent has what it needs to invoke and interpret it.

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 100%, so the schema already documents all five parameters including time-window formats and entity omission; the baseline is 3. The description roughly restates these (2-15 candidates, omit entity for private series) rather than adding format or syntax detail beyond the schema.

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?

States a specific verb and resource ('fits ONE multiple regression of the target on ALL candidates jointly') and explains exactly how it differs from the sibling find_drivers ('use this instead of find_drivers when candidates may overlap'). An agent can distinguish it without opening either schema.

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?

Explicitly names the alternative (find_drivers) and the condition that selects this one instead (candidates may overlap, or you need honest independent effect sizes). It also names the applicable data domains, so the selection decision is fully determined.

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