ssh_host_diagnose

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

No annotations are provided, so the description carries the full burden. It discloses a genuine behavioral trait (single round-trip, bundling many reads) and implies a read-only telemetry operation, but never states it is non-destructive, whether it needs sudo for some sections (Docker, ports), or what happens on connection failure. Partial coverage only.

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?

A single front-loaded sentence with no filler; the enumerated payload list is dense but each item earns its place by telling the agent what data it will get back. Slightly list-heavy but appropriately sized.

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 and no annotations, the description usefully catalogs the returned data categories, which is its main contribution. However, it omits auth/permission expectations, failure behavior, and confirms nothing about safety for a tool that opens an SSH session to a remote machine.

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?

One nested parameter with 100% schema description coverage, so the schema already documents host, port, profile, username, password, and privateKeyPath. The description adds nothing about the target/profile resolution beyond what the schema's own descriptions say (default profile 'homelab'). Baseline 3 is correct.

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 clear resource (remote host) and enumerates exactly what the snapshot returns: OS, kernel, uptime, load, RAM, disk, Docker, ports, top processes. This distinguishes it from ssh_exec (arbitrary command execution) without naming siblings. Specific and concrete, though it never explicitly contrasts itself with the exec/sftp family.

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?

Usage is implied rather than stated: 'in a single round-trip' hints that this is preferable to multiple ssh_exec calls when you want a broad host overview. There is no explicit when-to-use, when-not-to-use, or named alternative, so the agent must infer the routing decision.

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