neurover_prepare_generation

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

Adds substantial behavior beyond annotations: no credits are spent, unsupported settings are silently dropped with a warning, and the MCP rewrites @ref_N into @image_N in order. Against that, annotations already flag a non-read-only, open-world mutation, and the description never says what artifact is created or that workflow context/auth is needed.

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?

Front-loaded with the step and the no-charge guarantee, then reference mechanics, then prompt placeholders — a sensible information hierarchy with almost no filler. The Midjourney/Seedance asides are useful but make the block denser than it needs to be.

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?

Compensates for the missing output schema by telling the agent to inspect finalPrompt, the references table and warnings in the response, which is valuable. Still, with 14 parameters, nested reference objects and an unexplained required workflowId, an agent cannot fill this call in confidently from the definition alone.

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 has to carry everything, and it does well for references (ordering, optional field/role, file-field targeting) and prompt placeholders. But workflowId (required), type, model, modelId, account, quality, resolution, outputFormat and durationSeconds get no explanation at all, so roughly half the surface stays opaque.

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?

States a precise action pair: assemble the generation request and obtain its price, explicitly framed as 'ШАГ 1 основного процесса'. The clause 'кредиты НЕ списываются' cleanly separates it from neurover_submit_generation, so an agent knows this is the non-committal prepare stage without opening a schema.

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 step-1 framing plus 'Перед оплатой проверь...' establishes the ordering relative to a later paid submit call, which is real when-to-use guidance. It never names an alternative tool explicitly (submit_generation, prepare_run) or states when not to use it, so it stops short of full routing guidance.

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