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

Beyond the idempotent and non-destructive hints, the description reveals major behavioral effects: excluding voids the transaction's journal entry, stops the posting engine from re-deriving it, and removes the amount from every report. It also discloses the batch size limit of 500, giving the agent meaningful operational context.

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?

Three sentences with no filler. The core action and flag direction are front-loaded, followed by behavioral consequences and concrete use cases. Every sentence earns its place.

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 annotations covering idempotency and non-destructiveness, and an output schema present, the description supplies the crucial behavioral details, batch limit, and use cases. One minor ambiguity remains: the schema does not mark `transactionIds` as required even though the description implies transactions must be targeted.

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 low at 25%, and the description does add meaning for `excluded` (true/false) and `transactionIds` (up to 500 transactions). However, `companyId` and `reason` are left unexplained beyond their schema metadata, so the description only partially compensates for the coverage 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?

The description states a specific action—exclude up to 500 transactions or restore them—and names the exact boolean flag (`excluded=true/false`). It also clarifies the accounting consequence (voiding the journal entry and removing amounts from reports), which distinguishes it from related accounting mutation tools like deleting journal entries.

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?

Explicit use cases are provided: duplicates, personal spending on a business card, and transfers already recorded elsewhere. The reversible nature (put them back with `excluded=false`) is also clear, but the description does not name alternative tools or state when not to use this operation.

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