computer_batch

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

No annotations are provided, so the description carries the full behavioral burden, and it does: sequential execution, stop-on-first-error, allowlist gate evaluated at call time, per-action re-evaluation of the gate, and the critical coordinate-caveat that mid-batch screenshots do not update the coordinate frame for later clicks. These are non-obvious traits an agent could not infer from the schema and would otherwise get wrong.

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 purpose, then rationale, then the allowlist gate, then the coordinate caveat — a sensible ordering. Five sentences for a tool with this many non-obvious runtime rules is dense but earns its length; minor compression is possible but no sentence is 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 batch-execution tool with no annotations and no output schema, the description covers everything the agent must know: batching benefit, predictor condition, ordering/error semantics, auth gate behavior at both call and per-action granularity, and the coordinate-reference frame. Nothing about correct invocation is left to guesswork.

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% and the schema itself documents every sub-field (text, repeat, duration, coordinate, start_coordinate, scroll_amount). The description adds genuine cross-cutting semantics the schema cannot express: actions run sequentially, abort on first error, and that coordinates refer to the pre-batch screenshot rather than any mid-batch screenshot. Baseline would be 3 given full schema coverage; the pre-batch coordinate rule is strong value-add beyond the field descriptions.

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 a sequence of actions in ONE tool call') and immediately differentiates from the 20+ single-action siblings (type, left_click, key, etc.) by explaining that each individual call costs a model→API round trip. An agent can tell this is the batch counterpart to the singular tools without opening the schema.

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?

Explicit when-to-use with a concrete example ('click a field, type into it, press Return') and the selecting condition ('use this whenever you can predict the outcome of several actions ahead'). It also names the implicit alternative — the single-action siblings — via the round-trip contrast. No exclusions are needed beyond the predictability condition, which is itself the boundary.

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