zabbix_host_investigate

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds real behavioral context beyond that: the exact scope of collected data and the explicit contract that it 'reports facts and draws no conclusions; interpreting them is the caller's job,' which sets output expectations. It does not, however, mention result size, timeouts, or permission requirements.

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?

Three tight sentences, front-loaded with the core purpose, then scope, then routing. The 'draws no conclusions' clause is not filler — it changes how the caller should treat the response.

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?

With no output schema, the description carries the burden of describing return content, and it does so by enumerating the five data categories the snapshot includes. Combined with the explicit routing guidance and annotations covering the safety profile, an agent has everything needed to select and invoke this tool 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 100% and there is only one parameter, so the schema fully documents 'host' (name, fragment or identifier). The description never elaborates on the parameter or on how a fragment matches multiple hosts, so it adds nothing beyond the schema — baseline 3.

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 ('Collect') and resource ('diagnostic snapshot of one host'), then enumerates exactly what is gathered: host state, active problems, recent events, silent/unsupported items, maintenance windows. This is clearly distinguishable from siblings like zabbix_host_status and zabbix_unreachable, which it names.

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?

Gives an explicit trigger ('what is wrong with a named host' or 'one diagnostic pass instead of several queries') and names two alternatives with the conditions that select them: zabbix_host_status for a short status line, zabbix_unreachable for hosts Zabbix cannot poll. Nothing is left to inference.

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