zabbix_metrics_latest

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

Annotations already cover the read-only, idempotent, non-destructive profile, so the bar is lower, yet the description still adds high-value behavior: values are read from history because item.lastvalue returns a constant zero, the history type is derived automatically, and a wrong query silently returns nothing rather than an error. That silent-failure warning is exactly the kind of trait an agent cannot get from annotations.

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?

Front-loaded with the action, then the critical history caveat, then routing. Three short paragraphs with no filler, though the middle paragraph is dense enough that it could be trimmed slightly for a tool with only three parameters.

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 read-only metrics lookup with complete schema coverage and full safety annotations, the description covers purpose, caveats and routing alternatives. With no output schema, return details are rightly left to the schema's truncation note, so nothing an agent needs is missing.

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%, so host, limit and search are already fully documented including the 1-500 range, default of 25, and truncation reporting. The description adds only the general notion of a host-and-item lookup, which does not extend the schema, so baseline 3 is right.

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 ('Show the newest value of a host's items') and immediately scopes it to one host and one item set, which separates it from the history and investigate siblings. An agent can route correctly without opening any schema.

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?

Names the exact use case ('current value of an item, such as CPU, disk or a custom metric, on one host') and then gives two explicit alternatives with their selecting conditions: zabbix_metrics_history for a time window, zabbix_host_investigate for a host that stopped sending data. 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.