Save the configuration

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=true, so the bar is lower. The description adds real context the annotations don't carry: the write target (startup config) and the reboot-persistence effect. It stops short of noting that an existing saved startup config is overwritten, which is what makes the destructive hint non-obvious.

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 sentences, effect front-loaded before the usage caution, with no filler. Each sentence carries distinct information: what it does and when to invoke it.

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, zero params, and a flat schema, the description supplies enough to call the tool correctly: action, persistence effect, and the confirmation condition. The one gap is not stating that the previous saved configuration is replaced, which would fully explain the destructive annotation.

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 takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The absence of args is consistent with the description's framing as a single global commit action.

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 concrete verb and both resources ('writes the running configuration to the startup configuration') plus the observable consequence ('pending changes survive a reboot'). This clearly separates it from sibling read/backup tools like get_config_state and backup_config.

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?

Explicitly scopes when to call: 'Nothing else in this server saves, so call this only once the user has confirmed the changes are what they want.' That names the exclusivity relative to all siblings and imposes a confirmation prerequisite, leaving nothing to inference.

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