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

Annotations only carry the safety profile (destructiveHint, openWorldHint, readOnlyHint=false); the description goes well beyond that with a concurrency cap ('at most 5 run at once'), an idle reaper ('one nobody touches for 30 minutes is stopped'), and the no-terminal limitation. These are exactly the operational constraints an agent needs before committing to a long-running process.

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?

Three sentences, front-loaded with purpose, then follow-up tooling, then constraints. Every sentence carries distinct information; nothing is redundant with the schema or annotations.

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?

With no output schema, the description still tells the agent what comes back ('its first output') and how to retrieve more. Lifecycle, limits, and failure modes are all covered, so an agent can invoke and manage the process without further discovery.

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 100%, so command, cwd, device, and wait_ms are already documented in the schema. The description adds no parameter-level detail beyond the implied link between 'return its first output' and wait_ms, so the baseline 3 applies.

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 ('Start a command that keeps running') and immediately grounds it with concrete examples (dev server, build, Python or Node shell, ssh session), plus the return behavior ('return its first output'). This clearly separates it from one-shot siblings like run_command and from the process-lifecycle siblings it names.

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 routes follow-up work: 'Use read_process_output and interact_with_process to follow up and force_terminate to stop it.' It also states a hard when-not condition ('full-screen programs and password prompts will not work'), leaving nothing to inference about fitness for a task.

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