zabbix_detectar_anomalias

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It names the Z-Score method (useful) but says nothing about whether the operation is read-only, how much history it pulls, whether the threshold default of 2.5 sigma drives the verdict, or what volume of data is required.

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?

A single tight sentence is appropriately sized, but it opens with a stray '95.' numbering artifact that adds no meaning and pushes the actual content back. The remainder is front-loaded and waste-free.

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?

An output schema exists, so return values need not be described. But for a three-parameter analytical tool with zero schema coverage and no annotations, the description omits both the input semantics and the safety profile, leaving the agent under-informed to invoke it correctly.

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 0% for all three parameters. The description never mentions itemid, desvios_padrao, or limite_amostras, so an agent has no idea that desvios_padrao is the sensitivity threshold or that limite_amostras caps the sample window. It does not compensate for the coverage gap at all.

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?

States a specific verb and resource ('identificar anomalias estatísticas') plus the method (Z-Score), so the agent knows exactly what the tool computes. It does not differentiate itself from adjacent analytical siblings such as zabbix_comparar_periodos, zabbix_analisar_falsos_positivos, or zabbix_diagnosticar_coleta, which keeps it from a 5.

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?

There is no guidance on when this tool should be chosen, what prerequisites exist (does the item need history data first?), or which sibling to use for trend comparison instead. 'nos dados disponíveis' is the only contextual hint and it is too vague to route an agent.

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