Run a command as a managed, log-captured execution

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

With no annotations provided, the description carries full burden and thoroughly discloses behavior: auto-injection of LOG_PROBE_* environment variables, line-by-line stdout/stderr capture with stderr as level=error, merging with HTTP-posted logs, waiting for exit or timeout, and the requirement of prior probe_server_start. No contradictions exist.

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?

Every sentence delivers distinct value: the first explains the core subprocess launch and environment injection, the second covers log capture, the third describes waiting behavior, the fourth states the prerequisite, and the fifth gives usage guidance. No filler or redundancy.

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 covers the primary behavior, preconditions, log capture, and alternative tools, but it omits what the tool returns (exit status? run ID?) and does not explain the role of the required sessionId parameter. Since no output schema exists, this gap slightly reduces completeness.

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 only 43% (3 of 7 params), and the description does not compensate for the missing semantics. It mentions command and timeoutMs but adds little beyond the schema, and it ignores sessionId, cwd, args, and label entirely, leaving agents to infer their 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 clearly states the action: spawns `command` as a subprocess with environment variables injected, captures stdout/stderr as logs, and waits for exit. It also distinguishes itself from execution_create by recommending the latter for long-running services.

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?

Explicitly states when to use this tool: 'Best for scripts, one-off repros, and test runs' and identifies the alternative for long-running services. Also mentions the prerequisite that probe_server_start must have been called first.

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