Recortar / poner texto de marca sobre una imagen existente

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

Annotations indicate a mutating operation (readOnlyHint=false), and the description confirms this by stating it applies crop and overlay. It adds valuable context beyond annotations: it explicitly notes no OpenAI call (zero cost), warns about base64 payload size/truncation, and clarifies that overlay is applied after crop. The warning about base64 and the error-handling scenario enrich behavioral understanding.

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 two sentences, front-loaded with the core action and input sources, then providing use cases. Zero filler, and the cost/no-OpenAI note is efficient. It covers purpose, usage, and key constraints without 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?

Given 8 parameters (including nested objects) and no output schema, the description is fairly complete: it explains input types, use cases, and the special error scenario. It does not explicitly describe the return format, but parameter names like incluir_base64 and incluir_preview hint at output options. The lack of an output schema is not a gap because the description guides invocation sufficiently.

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% — every parameter has a descriptive set in the input schema. The tool description does not add parameter-level information that isn't already present in the schema (e.g., the order of overlay after crop is noted in the schema's overlay_text description). Per calibration, a baseline of 3 is appropriate when the schema handles parameter documentation fully.

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 action: 'Aplica crop_to y/o overlay_text' on an existing image, and lists input sources (URL, local path, base64). It clearly distinguishes itself from siblings by emphasizing it works on existing images and does not call OpenAI, setting it apart from image generation tools.

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?

Explicit usage scenarios are given: 'Úsalo para ajustar el texto de un thumbnail sin regenerar, o para recomponer cuando generar_imagen/generar_variacion devolvió tipo_error postproceso'. It also mentions the cost benefit ('costo cero') and references sibling tools by name, providing clear when-to-use and when-not-to-use context.

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