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

Annotations already declare readOnlyHint and idempotentHint, and the description reinforces these with 'Every call is read-only and idempotent.' More importantly, it discloses a critical behavioral trait beyond annotations: on invalid input, the tool returns an error object instead of raising a protocol error, with an example error message. This adds significant transparency.

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 about 10 lines, front-loaded with the core purpose, followed by a JSON example, then usage guidelines, and finally error behavior. Every sentence provides essential information, with no fluff or redundancy.

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 tool's simplicity (4 parameters, all with schema descriptions, output schema present), the description covers all necessary aspects: purpose, example, when-to-use, when-not-to-use, assumptions (normal approximation), error handling, and safety guarantees. It is fully complete for an agent to correctly select and invoke the tool.

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 baseline is 3. The description provides a concrete example mapping parameters to the output, and mentions the valid confidence levels (90/95/99) and constraints (n>=2, std_dev>=0) that are already in the schema but reinforced. The example and error formatting add practical context 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?

The description explicitly states 'Compute a confidence interval for a mean (normal approximation)' and provides a concrete input/output example. It distinguishes itself from proportion and two-group tools by referencing the sibling ab_test, making the purpose unambiguous.

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 advises 'Use on data already collected, for a mean' and warns 'Not for proportions or two-group comparisons - the data server's ab_test compares two proportions.' It also alerts about unreliability on small or skewed samples, providing clear when-to-use and when-not-to-use guidance with an explicit alternative.

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