server_job

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

With no annotations, the description carries the full burden and does disclose the key behaviors: five action modes, the read-only vs. mutating split, the preview-then-confirm pattern for cancel/clean, and that clean removes finished-job records. Gaps remain around what cancel does to a still-running process and any permission requirements.

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?

Purpose is front-loaded in one short sentence, followed by a compact enumerable action list and then the operating rules. Every sentence carries information; nothing is padded. The colon-list format is dense and scannable.

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?

Six params with zero schema descriptions and no annotations, but an output schema exists so return values need no explanation. The description covers most of what an agent needs to invoke correctly, with the unexplained host parameter the main omission.

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 0%, so the description must supply all parameter meaning. It enumerates the action values, explains as_root's semantics (jobs started as root), implies lines via 'last lines of the log', and implies confirm via the preview behavior. The host parameter is entirely unexplained, leaving one of six params undocumented.

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?

Specific resource (background jobs) plus origin ('started with background=true'), and an enumerated action set makes the tool's scope immediately legible. It implicitly distinguishes itself from server_run, which starts these jobs, though it never names a sibling. Clear, but sibling differentiation rests on inference.

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 says which actions are non-destructive and immediate ('list, status and output run right away') versus which need confirmation ('cancel and clean show a preview first'), and gives a hard prerequisite ('jobs started as root must be read with as_root=true'). It does not point at any alternative tool for job-related tasks, so 4 rather than 5.

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