probe_host

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

Annotations declare non-read-only, open-world, idempotent, non-destructive; the description adds the missing context that explains those hints — it opens an SSH connection to a remote machine and persists the collected facts. The only gap is that it doesn't say whether a new probe overwrites prior stored facts or how unreachable hosts are handled.

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?

Two sentences: the action and its outputs come first, the usage trigger second. No filler, no redundancy with the schema.

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 an output schema present, the description doesn't need to describe return values, and it covers the mechanism, data collected and invocation trigger adequately. What's missing is the persistence semantics (does it write into the host record consumed by get_host / claim_host decisions?) and failure behavior for an offline host.

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?

There is a single required parameter with 100% schema description coverage, and the schema already supplies the origin of the value ('Host id from list_hosts, e.g. build-pc'). The description adds nothing about the parameter, 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?

It gives a concrete verb chain (SSH, run probe script, store facts) plus an explicit enumeration of what is probed (GPU, RAM, processes, CS2 path/build), which is far more specific than a name restatement. It doesn't explicitly contrast itself with the closest sibling, get_host, which likely returns the already-stored facts.

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?

It states the timing and motivation clearly: 'Use before planning work on a host — e.g. to see if a game or a heavy GPU process is running.' That is genuine when-to-use guidance, but there is no when-not (e.g. reuse stored facts via get_host instead of re-probing) and no cost/latency warning about SSH round trips.

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