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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral context: the operation is asynchronous with two observable states ('Pronto' vs 'Ainda gerando') and it discloses what a successful call returns ('o link do MP4'). That is exactly the async-state and return-shape information annotations cannot convey.

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 short sentences, no filler: the identification/chain comes first, then the success case, then the pending case. Every sentence carries operational meaning and the state handling is front-loaded.

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 no output schema, the description compensates by explaining that a completed call yields the MP4 link, and it covers the incomplete case that would otherwise leave an agent stuck. For a one-parameter polling tool this is fully sufficient to call correctly.

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's schema description already states the id comes from aplicar_marca_dagua. The description repeats ('pelo id') without adding format, validation, or error semantics beyond it, so this is the standard baseline-3 case where the schema does the work.

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 verb and resource ('Consulta um vídeo') and explicitly traces it to the sibling tool that created it ('pedido em aplicar_marca_dagua pelo id'), which cleanly distinguishes it from aplicar_marca_dagua and the other siblings. An agent can identify this as the retrieval/polling counterpart without opening any schema.

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 gives explicit conditional guidance: when the result is ready it returns the link, and when it is still generating the agent should wait a few seconds and poll again. That is a complete when-to-call, what-to-expect, and retry policy in one short passage.

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