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

Annotations already provide readOnlyHint=true and idempotentHint=true, and the description reinforces these by stating 'Every call is read-only and idempotent, so after correcting the input it is always safe to retry.' It also discloses error behavior: 'this tool never raises a protocol error — it returns {"error": "..."},' which is beyond what annotations convey. No contradictions with annotations.

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?

Every sentence serves a purpose: definition, example input/output, usage guidance, limitation (causation), error handling, and idempotency. The description is front-loaded with the core purpose and immediately provides a concrete example. It is comprehensive without any superfluous language.

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 moderate complexity (two numeric arrays, statistical output), the description covers all essential aspects: purpose, input constraints (length, equality), output format (with interpretation and caution), error handling, and idempotency. The presence of an output schema is complemented by the example, so the return values are well 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?

The input schema has 100% description coverage, describing both x and y with types, minItems, and constraints. The description adds a concrete example of typical input ({"x": [1,2,3,4], "y": [2.1,3.9,6.2,8.1]}), which demonstrates the expected JSON structure and helps an agent format parameters correctly. This example provides meaning beyond the schema's textual descriptions.

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 clearly states 'Compute the Pearson correlation between two numeric series,' which is a specific verb+resource pair. It also distinguishes itself from the sibling growth_rates by explicitly noting 'Not for a single series over time (growth_rates).'

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 explicitly states when to use: 'Use when two equal-length numeric series may move together.' It also provides a clear exclusion: 'Not for a single series over time (growth_rates).' Additionally, it includes a cautionary note about association vs. causation, guiding appropriate interpretation.

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