running_stats

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered and the description need only add context. It clarifies the computed statistics but says nothing about the output shape (one result per position? n-window+1 rows?) or edge behavior such as a window larger than the data array — a real gap given no output schema.

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?

A single efficient sentence that front-loads the operation and enumerates exactly which statistics are produced. Nothing extraneous, nothing under-specified at the sentence level.

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 two-parameter pure-computation tool with no output schema, the description should at minimum convey the shape of the result and how boundaries are handled. Those are missing; what is present is accurate and sufficient to know what is computed but not what comes back.

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% and documents both 'data' and 'window' with the default of 5. The description adds only that the window is a sliding/running window, which is useful framing but no format or constraint details beyond the schema. Baseline 3 applies.

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: compute running (sliding window) mean, standard deviation, min, and max over a numeric array. The 'running/sliding window' qualifier is a meaningful differentiator. However, it never names the nearby statistics siblings (descriptive_stats, statistics_calc, variance_calc), so an agent must infer the distinction itself.

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 use case is implied by 'running (sliding window)' — compute per-window statistics rather than whole-array statistics. But there is no explicit when-to-use vs when-not guidance and no pointer to descriptive_stats for whole-series statistics, which is the closest competing tool.

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