host_exec

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

With zero annotations the description carries the full burden, and it does add real traits: sudo escalation, parallel execution (batch 10), per-host output tails, and journaling of the command. It stops short of the safety profile an arbitrary-execution tool needs - blast radius, default root execution, irreversibility - so the disclosure is partial rather than complete.

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?

Four short sentences with the core capability front-loaded and no filler; every clause carries information. Slightly under-elaborated rather than bloated, so it is efficient but not maximally informative.

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?

For a 9-parameter, annotation-free, arbitrary-command tool with no output schema, the description covers execution mode, output shape, and audit trail, but leaves safety framing and the dry-run/apply lifecycle entirely to the schema. Adequate, with a meaningful gap for such a high-risk tool.

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 78%, so the schema already documents most parameters thoroughly (planHash, timeoutSec, target grammar). The description adds only marginal semantics - 'Parallel by default (batch 10)' and 'through sudo when configured' - which lightly reinforce batch and asUser but do not extend the schema's own text.

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+resource ('Run an arbitrary shell command on hosts') and immediately positions it relative to siblings with 'For anything the dedicated tools do not cover', so an agent can tell it apart from host_inspect, host_logs, host_file_edit, etc. without opening a 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?

Explicitly gives the usage condition: a fallback for gaps the dedicated tools leave. However it names no concrete alternatives and no when-not conditions (e.g. don't use for file edits, service restarts), leaving the agent to infer the routing.

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