Iniciar ronda de capturas

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

Annotations provide no behavioral hints beyond non-read-only status, so the description carries the burden. It discloses meaningful behavior: the expected_owned_unique guard blocks incomplete OCR effects, and quantity_mode='minimum' preserves already-recorded higher quantities. It does not cover side effects if a round is already active, nor the response format, but it adds substantial behavioral context beyond the schema.

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 three concise sentences with no filler. It puts the core purpose first, then adds the two pieces of parameter guidance that are most likely to be misunderstood. 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 state-changing round-start tool, the description covers the essential invocation semantics well: what a round is, how it behaves across captures, and how to fill the safety-related parameters. It does not describe the return value or what happens when starting a round while another is already in progress, and label is still unexplained, so it is not fully complete.

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 50%, and the description compensates well for the two most nuanced parameters: expected_owned_unique is defined as the sum of visible header counters, and quantity_mode='minimum' is explained in terms of preserving superior existing quantities. Expansion is also contextualized as the scope of the round. Only the optional label parameter remains semantically undocumented.

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 uses a specific verb and resource: 'Crea una ronda para una expansión completa.' It also defines the round's lifecycle from first to last captured card, which clearly distinguishes this from sibling round tools like round_record, round_finalize, and round_status.

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 provides clear context for when to use the tool and how to set the critical parameters: a round is for a full expansion, expected_owned_unique prevents incomplete OCR from corrupting the collection, and quantity_mode='minimum' is appropriate for normal grids. It does not explicitly name alternatives or state when not to use the tool, but the guidance is still practical and unambiguous.

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