stats.ci_mean

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

Beyond the readOnly/idempotent annotations, it discloses the computation method (t-distribution, standard error from sample SD with ddof=1) and the output precision (float64 result rendered as a 10-significant-digit string), which materially affects how an agent interprets results. Annotations already carry the safety profile, and the description adds the method/rounding context that matters here.

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, front-loaded with the operation and return values, then parameter formats, then error/scope limits — no restatement of the name or filler. The density is justified because each clause adds a constraint the schema does not encode.

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 an output schema present, the description needn't detail return values, yet it names mean/lower/upper anyway. Combined with full parameter constraints, the ddof=1 standard-error basis, rounding behavior, and the proportion-interval exclusion, an agent has everything needed to call it correctly.

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 0%, so the description must carry the load and it does: `values` is specified as two or more Decimal strings, and `confidence` as a Decimal string strictly between 0 and 1 with default "0.95", plus the explicit failure mode for percentages. Both parameters have type, format, constraint, default, and error behavior documented.

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 (two-sided CI of a sample mean via t-distribution) plus the exact outputs (mean, lower, upper), so the agent knows precisely what it computes. It implicitly separates itself from stats.bootstrap_ci and proportion intervals by the closing scope note, but never names the sibling alternative, keeping it short of a 5.

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?

Gives a clear exclusion — it cannot be used for population proportion intervals — and warns that a percentage like 95 in `confidence` is an error, which is real usage guidance. It does not route the agent to stats.bootstrap_ci or any alternative when a non-t CI is wanted, so it falls short of explicit when/when-not/alternatives.

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