list_hosts

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

Annotations already cover safety (readOnlyHint, idempotentHint, openWorldHint=false), so the bar is lower; the description still adds real value by explaining that `stuck` is computed server-side from heartbeat freshness versus phase movement, and that `lock.stuck=true` means the owner may be hung. That is interpretation the schema cannot convey. It stops short of covering empty-list behavior or ordering.

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 what is listed, then the call-to-action, then the interpretation rule. Every sentence earns its place; the parenthetical field list and backticked field names are compact. Slightly dense line-wrapping, but no redundant restatement of the name.

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 and no parameters, the description only needs to cover purpose and how to act on results — which it does, including the non-obvious stuck-lock heuristic. Only minor gaps remain (whether an empty host list is possible, and which tool to use once a lock is detected).

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?

The tool takes zero parameters, so there is nothing to disambiguate and the baseline of 4 applies. The description instead spends its space on the semantics of returned lock fields, which is appropriate.

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?

Specific verb + resource ('List registered test/build hosts') plus an explicit statement of what is returned: facts (shell, GPU, paths) and current lock state. An agent can distinguish this from get_host (single host) or claim_host (acquire) without consulting schemas.

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?

'CHECK THIS before driving any host' gives an explicit pre-condition for calling, with the rationale (a fresh lock means another session/workstream owns it). It does not name the concrete alternative calls (get_host, probe_host, claim_host) an agent might use once it sees a lock, so it stops short of full routing guidance.

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