Экспорт конфигурации (бэкап)

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

Annotations only convey readOnly/idempotent/non-destructive; the description goes well beyond them by disclosing the critical trait: the result contains plaintext or weakly obfuscated secrets—password hashes, WPA-PSK, and WireGuard parameters. It also instructs the agent on safe downstream handling (not quoting secrets, writing backups to a file outside git), which is exactly the context an AI agent needs beyond the annotations.

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 longer than average, but every sentence earns its place: primary purpose is front-loaded, the web-UI equivalence adds precision, the 'ВАЖНО' section flags the security risk, and the final guidance prescribes concrete safe handling. Nothing is redundant or padded.

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?

With no output schema, the description correctly bears the burden of explaining the return value—full running-config as CLI text—and thoroughly covers sensitivity and storage handling. The only minor gaps are a lack of any note about the output potentially being very large or truncated, which is a small omission for a zero-parameter read-only tool.

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 tool has zero parameters and 100% schema description coverage, so the schema itself fully defines the parameter surface. Per the baseline for 0-parameter tools, the description does not need to compensate; it additionally implies that no configuration is needed, which matches the empty 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 states a precise verb ('Возвращает'), a specific resource ('полный running-config роутера'), and the output format (текст в CLI-синтаксисе). The reference to the web-UI Save button clarifies exactly what the tool returns and distinguishes it from the read-only sibling tools like get_version and get_system_info, which return only fragments of device state.

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 clearly establishes the use context: this is the config-backup/export tool, equivalent to the Save button, and it gives explicit operational conditions—warn the user before invoking and store results outside a git repository when a backup is requested. It stops short of naming alternatives or explicit when-not-to-use scenarios relative to siblings, so it earns 4 rather than 5.

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