prepare_batch_write

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 well: it discloses atomicity, same-initial-snapshot validation, ordered execution with version checks, no side effects ('Nothing is changed'), and whole-batch rejection with a zero-based item_index.

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 purpose and dense with useful information; every sentence contributes. Minor clarity issues like 'actual clarification' and the vague 'existing single-write discovery workflow' keep it from being fully polished.

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?

Covers nearly all critical behavior for a prepare endpoint: validation snapshot, ordering, version checks, no persistence, failure behavior, and the action_id result. The main gap is not explicitly stating that the returned action_id should be passed to commit_batch_write to apply the batch.

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 description coverage is 0%, but the description compensates by referencing prepare_write's argument shape and naming review_ids, decision_reason, and optional clarification. It also adds batch-level semantics like the 1–10 limit and successive expected_version requirement, though it does not enumerate operation/arguments fields explicitly.

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 ('Preview'), resource ('existing-record writes'), scope ('1–10'), and outcome ('returns one action_id'). The atomicity and batch nature clearly distinguish it from single-write prepare_write and commit_batch_write.

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?

Gives clear context: use for 1–10 existing-record writes, and explicitly excludes creation/collection changes by directing them to the single-write discovery workflow. However, it does not explicitly name commit_batch_write as the follow-up step or state when single prepare_write should be preferred.

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