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

Annotations already cover the safety profile (destructive, non-idempotent, open-world), so the description's real value is the added behavioral detail: the job survives the call returning and connection closing, output is written to a log read via job_status, and the command runs from the login user's home directory. Auth/permission requirements and any concurrency limits are not mentioned.

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?

Four tight sentences, front-loaded with the action and its immediate return, then usage, durability, and cwd. Every sentence carries distinct information with no repetition of 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 names the return value (job id) and explains where the actual output lands. Combined with annotations and a fully documented schema, an agent has everything needed to invoke and follow up 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 100%, so baseline is 3, but the description adds genuinely new parameter-relevant context: the working directory for `command` is the login user's home, and the username choice must match the one used for job_status/job_stop (reinforcing the schema note).

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 (start), resource (shell command), execution mode (background on a server), and the immediate return (job id). An agent can distinguish it from ssh_exec (synchronous) and job_status (reads output) purely from the description.

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 a concrete when-to-use rule — anything over ~a minute, with examples (installs, builds, backups, migrations, downloads). It routes follow-up work to job_status but never explicitly names ssh_exec as the alternative for short commands, so the exclusion is only implied.

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