get_metrics

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the metric categories but says nothing about whether this is a read-only snapshot, whether values are cumulative or windowed, whether the cache must be enabled, or how frequently the data refreshes.

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?

One compact sentence with the resource named first and the contents parenthesized. No filler, no redundancy, fully front-loaded.

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 parameters and a declared output schema, the return values need not be explained, so the description is nearly sufficient for correct invocation. The only real gap is sibling disambiguation against get_stats and similar metrics endpoints.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the schema is trivially complete at 100% coverage. Baseline 4 applies for a no-argument tool.

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 names a specific resource (DNS cache and DHCP metrics) and enumerates the contents (cache size, insertions, evictions, reply types), so an agent knows exactly what data comes back. It does not, however, distinguish this from the many sibling statistics tools such as get_stats or get_ftl_info, which likely return overlapping data.

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 statement of when to call this tool versus get_stats, get_ftl_info, or get_system_info. With roughly twenty sibling getters in the stats family, the absence of routing guidance leaves the agent to guess which endpoint holds cache/DHCP metrics.

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