Dokümanı doğrula

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

Beyond the readOnly and idempotent annotations, the description details behavior that is not visible in the schema: errors include a path and explanation, and an `ok=true` result indicates a saveable normalizedDocument. This adds genuinely useful behavioral context.

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?

Two short, front-loaded sentences deliver all necessary information: non-saving behavior, input alternatives, and output semantics. No redundant filler; every phrase adds value.

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 validation tool with nested inputs and no output schema, the description covers the input contract, the non-destructive nature, the error shape, and the conditions for a saveable result. It is sufficient for an agent to 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?

The description directly supplements the schema by explaining that the caller must provide either `sections` in authorship format or a full `document` with `{root, content, zones}`. It also highlights relevant inner fields like type/props/variant/slots, compensating for the top-level schema coverage gap.

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 identifies a specific action: validate a document without saving it. It defines the two accepted input forms (`sections` and `document`) and distinguishes the tool from page-management siblings by emphasizing it does not persist.

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 phrase 'without saving' and the kirjeld of the two accepted input formats provide clear context that validation is meant to be a pre-save check. Explicit alternative tools are not named, but the functional boundary is clear enough for an agent to select it.

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