execute_batch

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

With no annotations provided, the description fully carries the behavioral disclosure burden. It discloses the single undo transaction, automatic on-disk checkpoint, refusal when checkpoint saving fails, and cache update via modelPatch. It also explains the 'no way back' implication of skipCheckpoint. This is rich, non-obvious behavior clearly surfaced.

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 compact—three sentences—and front-loads the key 'preferred mutation path' concept. It is dense with jargon (ENTIRE_SCRIPT, modelPatch, dispatcher round-trip) which may reduce readability, but every sentence earns its place by adding workflow, alternative guidance, or flow context. It could be more scannable with a brief plain-language opener.

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 complex mutation tool with no output schema, the description covers prerequisites, process, safety gate, alternatives, and typical next step (summarize_changes). It does not state what the tool returns or how success/errors are surfaced beyond the checkpoint refusal, which is a notable gap. Because of the rich context provided, it remains highly complete overall.

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 high (83%), so the baseline is 3, and the schema already documents commands, timeoutSec, checkpointTag, skipCheckpoint, and transactionName well. The description adds workflow context by prescribing 'resolve targets → checkpoint gate' and noting the need for prior scan_document/analyze_page for role targets, which slightly enhances command parameter semantics. It doesn't add detail beyond the schema for other parameters.

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 clearly positions execute_batch as the 'Preferred mutation path' and explicitly contrasts it with execute_operation/layout_operation, distinguishing its role as the batch-level tool. It never states the simple phrase 'executes a batch of commands,' but the typical flow and the mention of 'combining ops' make the purpose evident. A direct verb+object statement would push this to 5.

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 gives explicit usage guidance: 'ALWAYS prefer this over execute_operation / layout_operation when combining ops' and provides a concrete typical flow. It also defines a key prerequisite for mutating batches (automatic checkpoint) and warns via skipCheckpoint when rollback is intentionally sacrificed. This is exemplary when-to-use and when-to-be-careful guidance.

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