grok_batch

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

With no annotations, the description carries the full burden and does so unusually well: all-or-nothing pre-validation against today's budget, per-job error isolation with batch continuation, and the exception class (budget/no-extension) that halts the run and marks remaining jobs 'skipped'. That is exactly the failure-mode detail an agent needs before spending budget.

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?

Front-loaded with the core action, then preconditions, then return/failure semantics — a sensible ordering with no filler. The inline job-object spec is dense and hurts readability slightly, but every line carries information.

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?

No output schema exists, and the description compensates by describing the return shape and skipped/error semantics. But several documented job fields (mode, size, max_side, keep_original, name) are named without any meaning, and `confirm_over` is never sourced — significant gaps for a zero-coverage nested schema on a costly generation 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 coverage is 0% and `jobs` is an untyped array of free-form objects, so the description does the schema's job by enumerating job keys (prompt, name, aspect, n 1..4 default 1, mode, max_side, size, keep_original, timeout_s, out_dir). It loses a point for leaving `confirm_over` as a dangling reference not defined here, and for not distinguishing top-level `out_dir` from the per-job `out_dir`.

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: running several image jobs sequentially as a single batch. It is clearly distinguishable in intent from grok_generate_image (single job), though it never names the sibling or explicitly contrasts with looping the single-job tool.

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?

Usage is implied by the batch framing and the description gives real operational preconditions (whole batch validated first, confirm=true required above `confirm_over` submissions, ask the user first). However, it never states when to prefer this over calling grok_generate_image repeatedly, nor any exclusions.

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