Прогнать сценарий

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

The description substantially enriches the annotations: it specifies that the dialog is not saved anywhere, delays are skipped, external requests and service-chat notifications are not executed, and — critically — that AI nodes call the real model and consume its limits. This last point explains why readOnlyHint=false despite the tool being a simulation, giving the agent an accurate cost/side-effect model that annotations alone could not convey.

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 efficiently organized: purpose is front-loaded in the first sentence, followed by a compact list of what is suppressed (saving, delays, external requests, notifications), then the variables usage tip, and finally the cost warning delivered with an explicit 'Внимание' marker. Every sentence carries distinct information, and the AI-limit caution is placed at the end where it reads as an important caveat rather than burying the main purpose.

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 7 parameters, a nested variables object, no output schema, and no annotation detail, the description is remarkably complete: it states the return-relevant results (trigger, steps, bot reply), enumerates exclusions, explains parameter usage for the trickiest param (variables), and discloses the real-world cost. It could go slightly further on what the simulated run returns structurally, but it compensates for the missing output schema better than most tool definitions at this complexity level.

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?

Schema coverage is 100%, so the baseline is 3 with the schema carrying the load. The description adds genuine value beyond the schema by explaining the purpose of the variables parameter — substituting conversation-accumulated state to exercise conditional branches and substitutions — which the schema's bare example ('{"город": "Москва"}') does not convey. Other parameters receive no description-level additions, but the schema already documents them well.

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 opens with a specific verb+resource combination — 'Проверяет сценарий, не выходя к платформе' — and concretely states what the agent gets out of it: which trigger fired, which steps executed, and what the bot would reply. It clearly distinguishes flows_simulate from sibling flow-management tools (flows_save, flows_publish, flows_delete) by framing it as a sandboxed test run rather than a platform operation.

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 gives clear context on when to use the tool: to verify conditional branches and substitutions by injecting accumulated conversation state via variables ('так проверяются ветки условий и подстановки'). It also communicates the safety profile so an agent knows it is the non-destructive option. It does not explicitly name alternatives or state when-not-to-use in favor of another tool, but the behavioral boundaries are clear enough to guide selection.

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