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

The description adds important behavioral context beyond the annotations, including that confirmations are written as 'a user override that AI enrichment never overwrites' (a durable persistence guarantee) and that unresolvable transactions return in failures. It also explains the state transition. Since the annotations already cover idempotency and non-destructiveness, these added details are valuable and not redundant.

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 fluff: the first states the core action and scope, the second explains the durable override behavior, and the third provides failure handling and the alternative tool. The most important information is front-loaded, and 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?

For a batch operation in a complex review flow, the description is sufficiently complete. It describes the action, state transition, behavioral guarantee (override not overwritten), failure mode, and the correct alternate path. The output schema and idempotentHint annotation cover return shape and retry safety, so no critical information is missing.

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?

The description partially clarifies the parameters: 'up to 500 transactions' maps to the transactionIds array with maxItems 500, and the phrase 'confirm the categories... for transactions' implicitly describes the transactionIds purpose. However, it does not explain the companyId parameter, and with schema description coverage at 50%, the description does not fully compensate for both parameters. The schema wrapper descriptions hold some of the load, but extra param-level guidance would lift the score.

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 clearly identifies the verb ('confirm'), the resource ('categories the posting engine chose'), the scope ('up to 500 transactions'), and the state change ('moving them from the pending tab to posted'). It also differentiates the tool from transaction_categorize_transaction, which the agent is directed to for unresolvable categories.

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?

The description explicitly states a key exclusion condition: transactions with no resolved category cannot be confirmed and will be included in failures. It then names the alternative (transaction_categorize_transaction) and instructs the agent to use it first in those cases. This provides direct when-to-use and when-not-to-use guidance, with a clear alternative.

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