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

Goes well beyond the annotations. destructiveHint=true only flags destructiveness, while the description details exactly what is reverted — account balance (and destination account if TRANSFER), linked goal if TRANSFER with goalId, card/invoice effect if cardId — conditioned on isPaid: true, and closes with 'Ação irreversível.' This is precisely the side-effect context an agent needs to predict the consequences of the call.

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?

A single dense sentence that front-loads the primary action and then lists structured conditionals. Every clause earns its place — no filler — but the run-on structure with nested qualifiers ('se TRANSFER', 'se TRANSFER com goalId', 'se cardId') is heavier to scan than a short bulleted breakdown would be.

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 single-parameter destructive tool, coverage is strong: the operation, the conditional side-effect cascade, and irreversibility are all present. The remaining gaps — behavior when the id does not exist or was already deleted, and return values — are largely covered by annotations (idempotentHint=true) and the output schema respectively.

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%: the single 'id' parameter already has a description ('ID da transação a excluir'), so the baseline of 3 applies. The description adds only indirect meaning by tying the id to transaction properties (isPaid, TRANSFER, goalId, cardId) that modulate behavior, but does not further define the parameter itself.

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 opens with a specific verb and resource — 'Exclui uma transação permanentemente' — making the operation unambiguous. The detailed cascade of reversals (balance, destination account, goal, card/invoice) clearly distinguishes it from siblings like update_transaction, create_transaction, and the confirm_* tools. The irreversibility warning reinforces the scope.

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?

Usage is implied rather than stated: the name and behavioral detail make clear this is for permanently removing transactions, but the description gives no explicit when/when-not guidance or named alternatives. It does not tell the agent when to prefer update_transaction or confirm_* tools over deletion, nor mention any prerequisites.

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