performance

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

With no annotations, the description carries the full burden and does a decent job: it discloses the return shape (promedio, p95 y maximo con su momento) and an infrastructure prerequisite (intervalos largos requieren vCenter). It still omits the time-zone/units context of hora_inicio/hora_fin and any rate-limit or cost notes.

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 metric enumeration is front-loaded, and the following lines are dense with parameter-level facts rather than filler. It is slightly long but every clause conveys new information.

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 7-parameter, annotation-free tool with no output schema, the description covers the metric set and three parameters well but leaves the VM selector, hour window, and labor-hour flag unaddressed, and does not clarify the relationship to historial_perf.

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 0%, so the description must compensate for all 7 parameters. It explains intervalo (with allowed values), max_muestras, and dias (as an alternative), but vm, hora_inicio, hora_fin, and solo_horario_laboral are never explained beyond the schema's bare titles and defaults.

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 resource (host and VM metrics) and enumerates the exact metric families returned (CPU uso, CPU Ready, Co-Stop, memoria activa/ballooning/swap, latencia de disco, IOPS), which is far more than a tautology. It does not, however, differentiate itself from the sibling historial_perf, which plausibly covers similar ground.

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 real operational guidance at the parameter level: intervalo values, the fact that day/week/month/year require vCenter, that max_muestras=180 equals 1 h in realtime, and that dias is an alternative to max_muestras. But there is no explicit when-to-use-this-vs-alternatives statement, and the overlap with historial_perf is left unresolved.

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