ops_run_command

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

With no annotations, the description carries the full burden and does well: it discloses automatic execution for known read-only diagnostics, the external-approval gate for mutations, outright denial of unknown commands/shell launchers/pipelines/escape primitives, and that approval routing is not model-controlled. It omits whether the call blocks waiting for approval, timeout behavior, and rate limits.

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 purpose is front-loaded in the first line and the policy statements are terse and information-dense. The closing DingTalk sentence is tangential to invoking this tool and is the one line that does not clearly earn its place.

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 no explanation, and the behavioral policy for a high-risk command execution tool is covered well. The remaining gap is parameter-level guidance for host_id, cwd, and reason, which an agent needs to populate the required fields correctly.

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 5 parameters, so the description must compensate and largely does not. It clarifies that 'argv' is a structured token array, but host_id, cwd, requester, and especially the required 'reason' (presumably the justification driving approval) are never explained. The DingTalk sentence adds an unrelated detail about delivery targets rather than parameter meaning.

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 gives a specific verb+resource ('Submit a structured argv command') and clarifies that input is a pre-tokenized argv rather than a shell string, which distinguishes it conceptually from a shell-execution tool. It does not explicitly name or contrast with siblings like ops_stage_script or ops_execute_approved, so it stops short of full sibling differentiation.

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?

It tells the agent what will happen for different command classes: read-only diagnostics may run automatically, mutations require external approval, and specific patterns are denied. However it never states when to choose this tool over ops_stage_script or ops_execute_approved, leaving the sibling-selection decision implied rather than guided.

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