ai_preview_schema

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

No annotations are provided, so the description carries full weight. It discloses the async nature (returns task ID, wait for result via ai_get_preview) and the separation from actual application (ai_apply_schema). However, it does not explicitly state whether this tool mutates the schema directly; 'modify' mode might confuse an agent into thinking changes are applied, though the workflow implies otherwise.

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?

The description is compact and front-loaded with the primary action, then adds mode details and the pipeline. The Args list is structured and each line serves a purpose. No wasted words.

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 tool that kicks off an async AI generation process, the description covers the necessary context: what it does, the two modes, how to proceed with results, and all parameters. The presence of an output schema means return values need not be explained. It is complete for correct invocation.

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?

With 0% schema description coverage, the description fully compensates by explaining each parameter: project_uuid, schema_uuid, prompt, mode (with allowed values 'create' and 'modify'), and current_schema (optional, used as context for modify). This adds essential meaning beyond the bare schema.

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 the tool's function: 'Запустить генерацию структуры схемы через ИИ' (launch generation of schema structure via AI) and that it returns a task ID. It distinguishes from siblings like ai_get_preview and ai_apply_schema by mentioning the workflow, showing this is the kickoff step.

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 explains when to use each mode ('create' for new schema, 'modify' for changes) and gives a clear workflow: run this, then wait via ai_get_preview, then apply via ai_apply_schema. It does not explicitly list alternatives or exclusions, but the workflow makes the tool's position clear.

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