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 disclosure that computation happens server-side and that only the named columns are decoded — a real cost/performance signal. It also sketches what each mode returns (per-column count/mean/std/quantiles/range, a correlation matrix, at most 500 resampled points), which matters because there is no output schema. It stops short of describing result structure or any plan/quota limits it alludes to.

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?

Two dense sentences with the mode enumeration front-loaded and no filler. Quoting the enum values in parentheses ties the prose directly to the schema, and the caps come last where they belong.

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 an 11-parameter, no-output-schema analytical tool, the description covers the modes, the result types, the column-decoding constraint, and the argument lineage to get_data. Gaps are minor: the shape of the returned objects is only hinted at, and the referenced "plan rules" are never explained.

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 every one of the 11 parameters is already documented inline, including the defaults and the 500-point / 12-column caps that the description repeats. The one genuinely additive phrase is "same slice arguments and plan rules as get_data", which points at constraints the schema does not encode, but the rest largely restates structured fields (numeric-only, default first 6).

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 names a specific operation (server-side statistics over a slice) and enumerates the three analysis modes with the exact enum values ("stats", "correlation", "resample"), so an agent knows what it will get back. It references get_data only for argument semantics rather than explicitly stating when to prefer this over get_data, so sibling differentiation is implied rather than spelled out.

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?

"for when you can't run code" gives a clear selection condition against get_data, which is the main competing sibling. It also tells the agent that slice arguments and plan rules are shared with get_data, reducing the need to re-derive them. There are no explicit when-not conditions or limits beyond the code-execution framing.

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