get_config_diff

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

No annotations are provided, so the description carries the full burden. It discloses the default rollback behavior, the meaning of rollback_id values, and the EOS version condition with graceful fallback. However, it does not mention potential side effects (e.g., whether the operation is strictly read-only), authentication requirements, or behavior for invalid rollback_id or config_path. Some behavioral context is added, but gaps remain.

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 brief and well-structured. It leads with the primary purpose, then concisely explains rollback_id options, and adds a single version note. Every sentence contributes useful information without redundancy or fluff. The format is easily scannable for an AI agent.

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?

The description is reasonably complete for the core diff operation, covering rollback_id behavior and version constraints. An output schema exists, so return value details are not needed. However, the meaning of config_path is not clarified, and the absence of annotations leaves safety and side-effect context under-specified. Given the tool's moderate complexity, the description covers the main points but has notable gaps.

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 must compensate. It thoroughly explains rollback_id, including default and numeric semantics. However, config_path is entirely unexplained, and hostname is self-evident. The description adds meaning for one of three parameters, leaving config_path ambiguous. This partial compensation suggests a mid-range score.

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 'Show config diff on an EOS device,' which clearly specifies the verb ('Show'), the resource ('config diff'), and the target ('EOS device'). It distinguishes itself from sibling tools like get_config (which retrieves the full config) and list_config_sessions by focusing on the diff operation. The rollback_id semantics add further specificity.

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 provides clear context for when to use the tool by explaining the rollback_id default behavior and the version dependency for startup-config diffs. However, it does not explicitly state when not to use this tool or mention alternative tools such as get_config for retrieving full configs. This is clear enough for straightforward use, but lacks explicit exclusion guidance.

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