fx_revaluation_reverse

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

Goes well beyond the idempotentHint/destructiveHint annotations: discloses the mirror-entry accounting mechanics, atomicity, the fact that original entries remain visible, refusal codes, and that the revert is terminal. Annotations say destructive but never explain what is written — the description does, consistently.

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-loads the operation, then behavior, then refusals, then consequence — logical and every clause carries information. Slightly dense with backticked codes and parentheticals, but nothing is padding.

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, non-reversible, no-output-schema mutation this covers safety profile, required inputs, refusal taxonomy, idempotency, and accounting consequence. An agent can decide and call it correctly without further lookup.

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?

With 0% schema description coverage the description must carry parameter meaning, and it does for runId (source run) and idempotencyKey (dedup key), plus defines the failure semantics tied to them. workspaceId is left implicit, which is the only gap.

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 ('Revert a posted FX revaluation run') and adds the document/category reference (D129 Q2) so the operation is unambiguous. It is clearly distinguishable from post_fx_revaluation, which it names as the producing sibling.

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?

Explicitly ties input to the sibling ('runId is the run post_fx_revaluation returned'), states the ordering rule ('revert newest first') via later_run_exists, and enumerates the exact refusal states that mean the agent should not call it.

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