Computer Batch

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

With no annotations, the description must carry behavioral disclosure, and it does cover ordering, coordinate space ('same screenshot-space rule'), and the return shape (one result line per action). It says nothing about the failure model, which is the critical unknown for a batch tool — whether a failing action aborts the remaining actions or the batch continues, and whether completed actions can be undone.

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 value proposition and the batching constraint, with no filler sentences; the inline example is load-bearing rather than decorative. The telegraphic phrasing and the bare pointer to a 'screenshot-space rule' defined elsewhere make it slightly harder to parse than it needs to be.

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 output schema covers the return value, so omitting return detail is fine, but with no annotations and an opaque array parameter the description is the only safety and failure-model signal available — and it omits error/partial-failure behavior for a multi-action tool. Adequate to invoke, not complete enough to predict outcomes.

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% — the single `actions` parameter is an untyped array of free-form objects with no property documentation — so the description must compensate, and it does: it specifies the per-item shape ({"action": <member name>, "input": <args dict>}) and supplies a three-element example. It stops short of enumerating the admissible action names or stating that they are the sibling tool members.

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?

A specific verb and resource — run multiple actions in one call — plus the discriminating property ('milliseconds apart in ONE call') that separates it from the single-action siblings like computer_click and computer_key. It also states why such batching matters (timing-critical UI, menus that close on blur).

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 when-to-use condition is explicit: timing-critical sequences where per-action latency would break the interaction. What is missing is an explicit exclusion — it never says to prefer the individual tools for ordinary, non-timing-sensitive steps.

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