ensp_send_command

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

With no annotations, the description carries the full burden, and it does disclose meaningful behavior: the errored flag is defined as the presence of 'Error:' in device echo, and the recovery flow (fix command, retry, do not continue) is spelled out. It stops short of covering session/auth prerequisites, timeout behavior, or side effects on device state.

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 tight paragraphs: purpose and return values first, error-handling guidance second. Front-loaded and free of filler, though the phrasing is dense enough that a slightly clearer separation of the error semantics would help.

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?

An output schema exists, so return values need not be re-explained, and the description correctly focuses on interpreting errored/errors. Still missing for a command-execution tool: session targeting semantics, timeout behavior, and routing versus the batch and system-view siblings, so it is adequate but not complete.

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% across three parameters, so the description must compensate and largely does not. It never explains session_id_or_name, what the timeout unit/behavior is (default 10), or expected command syntax (config-mode vs exec-mode), leaving all parameter meaning to bare property names.

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 specific verb-and-resource combination ('下发单条命令' / send a single command) and enumerates what it returns (output, elapsed time, error flag). The word '单条' (single) implicitly separates it from the batch sibling ensp_send_commands, but that sibling is not named explicitly, so the differentiation is left to inference.

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?

Gives concrete operational guidance for the failure path: when errored=True, correct the command from the errors echo and retry rather than proceeding with further configuration. However, it never states when to prefer this tool over ensp_send_commands (batch), ensp_enter_system_view, or the diagnostic siblings, so the choose-this-vs-alternative question is left partly unanswered.

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