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

The description matches annotations: read-only and idempotent are explicitly stated, and it adds richer behavioral detail: no protocol errors, returns a structured error object, and shows sample success/failure outputs. No contradiction found.

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 contributes meaning: purpose, domain rules, example, usage scope, error behavior, and safety guarantee. The structure is front-loaded and easy to scan, with no wasted content beyond perhaps 'FREE.'

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 simple validator with full schema coverage and a known output schema, the description covers validation context, alternative tools, error handling, and retry safety. It provides enough information to invoke the tool correctly without guessing.

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 schema already documents all three parameters. The description goes beyond by explaining validation rules for namespace/key (lowercase, underscores, no capitals/dashes) and what invalid input produces. It does not add much about value_type, but the schema already covers that.

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?

Description opens with a specific verb and resource: 'Validate a metafield namespace and key before you define it.' It clearly distinguishes itself from product_csv_check, and the example shows exactly what the tool does.

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?

Explicitly says 'Use when designing metafields' and 'Not for the CSV column that carries them — that is product_csv_check.' It also explains error/retry behavior so an agent knows when it is safe to call again.

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