device_fetch_config

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

With no annotations, the description must carry the full behavioral disclosure. It does so by noting that on command failure or timeout no config file is written, and by detailing the diff output variants (identical, onlyOnDevice, onlyInFile, unifiedDiff with context, preserving line order and duplicates). This adds real behavioral context beyond what any schema would show. It does not mention permissions or side effects, but the failure/timeout note is a strong positive.

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 three sentences: the first states the core purpose and the two optional parameters, the second details the diff behavior, and the third notes failure behavior and the login-parameter reference. It is front-loaded and free of fluff, though the third sentence could be merged to reduce length slightly.

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?

For a tool with 8 parameters and an output schema, the description covers the main operation, the diff output, and failure behavior, but leaves most parameter semantics to inference or a sibling reference. Since an output schema exists, return-value documentation is not required, but the lack of explanation for 6 parameters makes the tool only partially self-contained.

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 description coverage is 0%, so the description must compensate, but it only explains two of eight parameters: save_to (writes a UTF-8 file) and compare_with (compares with a baseline). The remaining parameters (host, target, username, password, topo_path, new_password) are not explained; the note that login parameters are same as device_exec is a reference, not an explanation. This leaves most parameter semantics undefined.

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 clear verb-object pair ('读回运行配置' = read back running config), states the resource and core operation, and immediately adds optional save/compare capabilities that distinguish it from siblings like device_push_config (which pushes configs). This gives an agent a precise idea of the tool's role.

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 implies when to use the tool (whenever you need to read a device's running config) but never states explicit alternatives or exclusions. It references device_exec for login parameters but does not say 'use this instead of X' or list conditions that would make another tool preferable. The guidance is adequate but not directive.

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