ssh_run_many

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

With no annotations, the description carries the full burden and does meaningful work: it discloses that each host applies its own allowCommands/denyCommands policy, that one host may be refused while others run, and that per-host status is reported rather than failing the whole call. Missing are auth requirements, parallelism/concurrency limits, and the interaction between timeout and stop_on_error.

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 the core action, then usage examples, then the key behavioral caveat. No filler and every sentence carries information.

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?

An output schema exists, so return values need not be explained, and the description still adds the useful 'one result per host' framing. For a 4-parameter fan-out tool with no annotations, the omission of timeout semantics and any auth/parallelism notes keeps it from being fully complete.

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 0%, so the description must compensate for four undocumented parameters. It clarifies that 'hosts' is a multi-host fan-out and 'command' is identical across hosts, and it implicitly characterizes the default stop_on_error=false behavior ('per-host status is reported rather than failing the whole call'). However, 'timeout' is entirely unaddressed and stop_on_error is only implied, leaving real gaps.

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 and resource ('Run the same command across several hosts in parallel') plus the output shape ('one result per host'), which cleanly distinguishes it from the single-host ssh_run sibling. An agent can pick this over ssh_run without opening either schema.

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 four concrete usage scenarios (compare versions, fleet-wide service check, restart several boxes, survey disk usage) that map well to when this tool is appropriate. It stops short of naming alternatives or stating when not to use it (e.g. single host → ssh_run), so it is clear context without explicit exclusions.

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