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

Adds substantial context beyond annotations: keyless auth over a tunnel, no inbound port needed, fresh shell per call (cd does not persist), ~90s hard cap, and the nohup background pattern. Annotations only flag destructive/non-idempotent; the description explains the operational envelope that an agent must respect.

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 tight sentences, front-loaded with what it does and its return shape, then constraints, then the long-job workaround. Every sentence earns 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?

Covers auth model, per-call isolation, timeout ceiling and long-job pattern, which is everything needed to invoke correctly. It does not spell out what 'combined output' looks like (stdout+stderr interleaved?) or exit-code handling, a minor gap for a tool with no output schema.

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 coverage is 100%, so baseline is 3. Description reinforces host/command semantics and — importantly — the timeout guidance ('keep a call under about 90 seconds') that qualifies timeoutSeconds, adding meaning beyond the schema's own 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 (run) and resource (a single shell command on one of your servers) plus behavioural scope: combined output and exit code. Distinguishable from siblings like sftp_read/write (file transfer) and data_query (structured queries).

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?

Explains the keyless tunnel model and points at hosts_list indirectly via the host parameter. It also says when to deviate: long jobs should be backgrounded and polled with later calls. No explicit exclusion of alternatives (e.g. running scripts vs one-liners), but the context is clear.

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