device_push_config

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

With no annotations provided, the description carries the full burden. It discloses key behaviors: automatic entry into system view, handling of #-segmented display current-configuration text with sub-view exit/re-entry, default stop-on-error and no-save behavior on errors, no automatic rollback, commit-before-save when CE prompt indicates uncommitted changes, and failure status on save exceptions. This is thorough, though it could clarify the interaction between the 'save' default and error-path behavior more explicitly.

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 compact, using a few sentences to convey a wealth of information. It front-loads the core purpose and constraint, then follows with behavioral details. It is dense but not verbose, and each sentence adds value. The structure is logical, though it could benefit from bullet points for scannability.

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 the tool's complexity (10 parameters, no annotations) and an output schema that likely covers return format, the description covers most essential behaviors and the key config-file constraint. However, it omits explanations for several parameters and does not mention error handling specifics beyond save failures. It is adequate but not fully complete for an agent to call it confidently in all edge cases.

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. It clarifies the exclusivity of config/config_file, references device_exec for credential parameters, and states save's default. However, it does not explain host, target, topo_path, or stop_on_error beyond the implicit mention. While these may be inferable from names, the description fails to fully document all ten parameters, leaving gaps for an agent.

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 clearly states the tool pushes configuration from text or a UTF-8 .cfg file, with a precise constraint that config/config_file must be chosen exclusively. This distinguishes it from siblings like device_fetch_config (fetch) and device_exec (execute commands). The verb 'push' and resource are specific, making the purpose unmistakable.

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 mentions that username/password/new_password are the same as device_exec, hinting at shared context, but does not explicitly state when to use this tool versus device_exec or device_fetch_config. There are no clear exclusions or conditional routing cues, leaving the selection logic mostly to the agent's inference from the purpose.

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