box_exec_background

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

The annotations already signal readOnlyHint=false and openWorldHint=true, and the description adds meaningful context: it runs via nohup, under a specific job directory, and returns immediately. This goes beyond the annotations, though it does not elaborate on how to monitor or clean up the job, which would have made it richer.

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?

The description is a single, front-loaded sentence of about 11 words that clearly conveys the action, method, and immediate return. There is no redundant information or 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?

The description is adequate for a tool with two simple parameters and no output schema, covering the core contract: what it does, how (nohup under job dir), and that it returns immediately. It does not mention how to check job status or that sibling tools exist for that, but this is not critical for using the tool correctly.

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% with both parameters described adequately ('Box id (bx_…)' and 'Shell command to run in background'). The description adds the 'nohup' and job-directory context, but these are more behavioral than parameter-specific, so it does not substantially enhance parameter understanding.

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?

The description uses the specific verb 'Start' and names the resource ('long command via nohup under .mcp-box-jobs/<jobId>/') and clearly states it returns immediately. This distinguishes it from synchronous execution tools like box_exec and from status-checking tools like box_job_status.

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?

The description implies usage for long-running commands by mentioning 'long command' and 'return immediately', but it does not explicitly state when to prefer this over alternatives or provide exclusions. There is no mention of sibling tools or a clear 'use this when' directive.

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