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

Even with destructiveHint=true already present, the description adds real value by clarifying that this is a bulk asynchronous job, that unsaved edits are ignored, and that it returns a requestId for status tracking. It does not go into reversibility or failure modes, but it meaningfully supplements the annotations.

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?

It is a single dense sentence with no filler. The purpose comes first, and every subsequent clause adds important operational detail: destructiveness, unsaved-edit behavior, preview-first advice, and requestId tracing.

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 bulk mutation with no output schema, the description supplies the critical information an agent needs: scope, side effects, preflight expectations, and how to observe the result. Together with the well-covered input schema and annotations, it is sufficiently complete for safe invocation.

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?

Both parameters have complete descriptions in the input schema, so the 100% schema coverage baseline of 3 applies. The description does not add additional meaning about workspaceRef or portfolioRef, but that is an accepted trade-off when the schema is already thorough.

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 uses a specific verb-resource combination: it re-runs current saved rules and counterparty defaults across eligible existing accounting transactions. This clearly separates it from siblings like preview_accounting_rules, edit_accounting_rules, list_accounting_rules, and delete_accounting_rule.

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?

It gives explicit on-the-job guidance: preview first and then track the returned requestId with get_request_status. It does not explicitly state when not to use it or name a fallback alternative, so it stops just short of the strongest usage guidance.

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