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

Annotations declare destructive/non-idempotent, but the description goes well beyond them: a 45-second hard deadline, exit 3 meaning unknown outcome with writes possibly landing within seconds, and the explicit warning not to repeat mutations after a timeout or lost response. This is exactly the operational context an agent needs to avoid duplicate destructive writes.

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?

Dense, front-loaded prose: what it is, how to start, where it executes, then the failure semantics that matter most. Every sentence carries unique information and none are padding.

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 destructive, timeout-bounded remote-exec tool with an output schema present, the description covers execution model, input conventions, exit-code semantics, and post-failure recovery. Since an output schema exists, it correctly avoids describing return payloads.

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 coverage is 100%, so the schema carries the baseline; the description still adds non-obvious meaning by telling the agent to pass text for --stdin commands via the stdin parameter and that the command string is what would follow 'ssh WORKSPACE.AGENT'. Modest but real value beyond the schema.

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 one Comment.io command or restricted shell script in your workspace') and pins down the execution model with 'exactly as an SSH exec: same commands, output and exit codes.' An agent knows precisely what class of operation this is without opening the 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 an explicit starting action ('Start with {"command":"help"}'), clarifies the execution locus ('runs on Comment.io, not on your machine'), and prescribes recovery behavior after failure ('reread state rather than repeating a mutation'). There are no sibling tools, so no alternative routing is needed.

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