bash

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

Annotations already declare destructiveHint=true and openWorldHint=true, so the safety profile is covered. The description adds non-obvious behavior beyond that: no shell state persists between calls, commands run with SSH account permissions, and background jobs must be tracked via job_output/job_kill on the same target. Missing detail on what a call returns (stdout/exit status).

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, front-loaded with the core action and scope. Every sentence carries distinct information: execution model, permission context, background workflow, and dependency requirement. No filler.

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, open-world tool with 6 parameters and no output schema, the description covers execution model, permissions, async workflow, and dependencies. It is nearly complete, with only the return shape (output/exit code) left implicit.

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 baseline is 3. The description goes further by explaining the run_in_background flow (job_id, same target) and the constraint that the shell is fresh per call, adding semantics the schema alone does not convey about how parameters interact across invocations.

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 ('Execute bash on the selected remote host') and immediately scopes behavior with 'Each call starts a fresh shell.' This clearly separates it from local file siblings like read/write/edit/grep/glob, which operate on the workspace rather than a remote host.

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?

Explains the background-job branch explicitly: 'Background jobs return a job_id; use job_output/job_kill with the same target,' which routes the agent to the correct siblings. It also states the prerequisite (remote Linux requires bash and python3). It does not, however, tell the agent when to prefer remote bash over the local read/grep/edit tools.

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