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

Beyond the readOnlyHint=true annotation, the description discloses the key behavioral traits: the link is static and not saved on the server, no account is required, furniture auto-distributes in a row when position is omitted, and the link opens an editor with view/move/adjust/budget capabilities. The explicit 'no se guarda en servidor' statement is consistent with readOnlyHint=true rather than contradicting it — the tool generates a link with no persistent side effects.

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?

Purpose is front-loaded in the first clause, and every subsequent sentence carries distinct information (use case, prerequisite, parameter model, static-link limitation, no-account requirement). It is a somewhat dense single paragraph with a keyword tail, so it is not maximally scannable, but there is no redundancy.

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 tool with deeply nested furniture params (15+ kinds, nested column/zone objects) and an output schema present, the description covers everything needed to call it correctly: return artifact format, usage trigger, prerequisite call, parameter alternatives, optionality semantics, and the static-link/no-account limitation. The existing output schema relieves it of needing to document return values.

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 description coverage is 100%, so the baseline is 3, but the description adds orchestration semantics the schema cannot convey: the preset-or-params mutual exclusion per furniture, that posición and rotación are optional with an automatic row-layout fallback, and the dependency on listar_presets for preset IDs. That pushes it clearly above baseline.

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 names a specific verb+resource ('Crea una escena 3D con uno o varios muebles'), the precise output artifact (an editable /d/<code> link that opens the Mueblito editor), and the multi-furniture scope. This inherently distinguishes it from siblings like ver_mueble (single piece) and cotizar_mueble (budget), even though only listar_presets is named explicitly.

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 an explicit trigger ('Usala cuando el usuario quiere visualizar cómo quedarían los muebles en un espacio o compartir un diseño con un carpintero o cliente') and a prerequisite that routes the agent to listar_presets when preset IDs are unknown. It stops short of a 5 because it never states when NOT to use it, and it mentions the editor can generate a presupuesto without clarifying that cotizar_mueble may be the right tool for budget-only requests.

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