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

Annotations already establish read-only, idempotent, non-destructive behavior, and the description adds meaningful cost information (paid, ~2 credits / $0.02), the batch capability, and the output shape. This is useful context beyond the structured metadata.

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 cover purpose, usage context, mode/input mapping, output, and cost with no filler. The most important information is front-loaded in the first sentence.

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 moderate complexity (5 parameters, mode enum, output schema), the description covers the overall workflow, parameter selection, output, and cost in a compact way. The output schema and input schema take care of the remaining structural detail.

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 covers all 5 parameters, and the description adds a useful mode-to-parameter mapping: 'sample for draft; schema+instance for validate'. It doesn't explain the legacy 'draft' boolean or the 'both' combination in depth, but the schema fills those details.

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 both actions ('Draft a JSON Schema from a sample object', 'validate an instance against a schema') and says they can happen in one call. It is immediately distinguishable from the sibling tools, none of which cover JSON Schema generation or validation.

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 'Call before writes' guidance gives an explicit use case, and the comparison to LLM inference tells an agent when this tool is a better fit. It does not explicitly cover exclusion cases or name alternatives, so it misses the top criterion.

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