correct_transaction

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

Goes well beyond the annotations: it explains optimistic-concurrency guards (per-entity observation count and expected snapshot), full rollback on conflict, denied write, or snapshot mismatch, and the correct idempotent retry pattern. Together these disclose what gets undone and how to recover safely.

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?

Five short sentences, each carrying a distinct payload (purpose, required inputs, rollback, retry, authorization limit), with the core action front-loaded. No 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 destructive, multi-entity mutation with no output schema, the description covers atomicity, failure/rollback, idempotency, and authorization boundaries well. Remaining gaps are the shape of the result and the per-entity change structure.

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% and the schema is nested, so the description must carry the load. It clarifies the two most subtle fields ('loaded observation count' and 'expected fields') and the retry key, but never explains 'changes', 'entity_id', or 'entity_type', leaving much of the schema undocumented.

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 with scope: 'Atomically compare and correct declared fields on multiple entities.' The atomicity and multi-entity scope implicitly separate it from the sibling 'correct', but no sibling is named, so it stops short of explicit differentiation.

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?

'Retry the identical request and key after uncertainty' gives concrete operational guidance, and 'does not authorize application-level approval' sets a scope boundary. However, no alternative tool is ever named, so the when-to-use-this-vs-'correct'/'merge_entities' question is left to inference.

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