enaho_sondear_llaves

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

The description discloses behavioral traits beyond the annotations: it downloads modules if needed ('Descarga los modulos si hace falta'), examines real data characteristics (cardinality, uniqueness, overlap), and always returns `inferido: true`. This adds context about side effects and output semantics that annotations (readOnlyHint=false, idempotentHint=true) do not specify.

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 longer than the minimal two-sentence example but is front-loaded with purpose and usage. Each sentence provides useful context (when to use, what it does, how to interpret results, when not to use). It is somewhat verbose with stylistic emphasis, but not wasteful.

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 complex inference tool, the description covers the essential decision-making context: why it exists, when to use it, what it does (download and inspect data), what the result always includes (`inferido: true`), and how to validate before publishing. The existence of an output schema means return details don't need to be spelled out. This is complete for the tool's complexity.

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 75%, and the description adds limited parameter-specific meaning beyond what's already in the schema. The `modulos` parameter's need for at least two modules is already described in the schema; the description reinforces it but does not add new semantics for `anio` or `corte`. Baseline 3 is appropriate.

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 opens with a clear verb+resource: 'Descubre como unir dos modulos de una encuesta que nadie ha curado' (discover how to join two modules of an uncured survey). It further distinguishes itself from sibling `enaho_unir_modulos` by specifying it is for cases where that tool fails due to missing declared keys, and from profile-based tools by saying curated knowledge wins when a profile exists.

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?

Explicitly states when to use: 'Usala cuando `enaho_unir_modulos` falle porque la encuesta no tiene llaves declaradas' (use when enaho_unir_modulos fails because the survey has no declared keys). Also gives a clear exclusion: 'Para las encuestas que SI tienen perfil, no uses esto' (for surveys with a profile, don't use this), naming the alternative approach.

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