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

Beyond the annotations (which indicate mutation but no destructiveness), the description discloses that both sides of the transfer are generated and linked (origens TRAP/TRAR), and that incorrect simulation pollutes reconciliation. This adds meaningful behavioral context that annotations do not cover, though it stays focused on the core operation.

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 description is a single paragraph with high information density, front-loaded with the purpose and a clear directive. It uses emphasis (ALL CAPS) effectively and avoids redundant wording, though it is slightly verbose for its length.

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 financial mutation tool with no output schema and low parameter coverage, the description covers the essential behavioral facts (two linked entries, reconciliation impact) and input nuances. It omits details about return values and error handling, but these are less critical for an agent correctly selecting and invoking the tool given the description's strengths.

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 0%, so the description must compensate. It does so for `conta_origem`/`conta_destino` (accepts name or id, resolved server-side) and `data` (format flexibility), but leaves the other six parameters unexplained. This is a partial compensation for the coverage gap, not a full one.

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 states it transfers money between two company checking accounts, specifies the internal operation (IncluirLancCC with `transferencia` block), and explicitly warns against simulating with separate entries. This distinguishes it from other financial tools without needing to open schemas.

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 explicitly declares this is the right operation for transfers and provides a strong when-not-to-use instruction ('não faça uma saída + uma entrada separadas'). It also gives practical input guidance (account name/id, date formats), leaving no ambiguity about when to choose this tool over siblings.

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