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

Annotations only say readOnlyHint=false and destructiveHint=false; the description adds the essential behavior: it writes accruals, is idempotent because positive-accrual rows are skipped, mirrors compute_close's engine, and requires a connected Aurgus account. That is exactly the beyond-annotation context a caller needs for a mutation tool.

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 verb and engine scope are front-loaded, and each clause carries weight (eligibility trigger, idempotency, param behavior, return value, auth). It is dense and slightly overpacked with parentheticals, but no sentence is wasted.

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?

With one optional param and no output schema, the description covers everything the agent needs: trigger condition, mutation semantics, idempotency, parameter effect, return value (events created plus accrual total), and the account prerequisite.

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 100% and the single parameter is fully documented in the schema itself ("Recompute just this agreement. Omit to recompute all active agreements."). The description restates the same distinction without adding format, constraints, or examples, so the baseline 3 applies.

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?

"Re-run the deterministic engine over the POS data" is a specific verb + resource, and the description immediately distinguishes the tool from compute_close by noting it posts the same provisional accruals. An agent can tell what it does and how it relates to the closest 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?

It explains when this is the right call — rows that just became eligible after a data fix or rule change — and states that already-accrued rows are skipped so a repeat run is unnecessary. It stops short of naming an explicit alternative or exclusion case (e.g. when to prefer close_agreement), keeping it at 4.

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