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

Beyond the annotations' read-only/idempotent profile, the description discloses the error contract: it never raises a protocol error and instead returns {"error": ...} with corrective guidance, plus an explicit safe-retry guarantee. That is exactly the non-obvious behavioral context annotations cannot express.

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-loaded with purpose, then usage, then errors — a sensible order. However, the fully spelled-out sample output duplicates information already carried by the output schema, and the stray 'FREE.' fragment is a minor structural blemish.

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 one-parameter, read-only statistics tool with an output schema, the description covers purpose, alternatives, error handling, and retry safety. An agent has everything needed to select and invoke 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 coverage is 100% and the single parameter is already documented with a minItems constraint, so the baseline is 3. The concrete input example {"numbers": [12, 15, 14, 90, 13]} adds working-format intuition beyond the schema, but no extra constraint or edge-case guidance (e.g., empty arrays) is offered beyond what the schema already says.

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 ('Describe a numeric dataset') and enumerates what is produced (center, spread, quartiles, outliers). It also names the sibling tools it is not, so an agent can distinguish it from confidence_interval and sample_size without opening any 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?

'Use as a first summary of one numeric dataset' gives the positive condition, and 'Not for interval estimates (confidence_interval) and not for planning a study (sample_size)' gives explicit exclusions with named alternatives. Nothing about routing is left to inference.

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