caddy_metrics

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds substantial behavioral context: output can be megabytes, filter-mode drops blank/free-form comments but preserves HELP/TYPE lines, '# EOF' is always kept, max_lines defaults to 500, and a trailing comment reports dropped lines. This goes well beyond the structured hints.

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 description is appropriately sized—four sentences that lead with the core purpose, then dive into parameter behavior with examples. Every sentence carries unique, essential information; there is no repetition or filler. The structure flows logically from purpose to usage to edge cases.

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 tool with no output schema, the description covers the return format implicitly (Prometheus text) and explicitly covers filtering semantics, line handling, size limits, and the trailing summary. It gives the agent enough context to anticipate output characteristics and pitfalls, making it complete for invocation and result handling.

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?

Although schema coverage is 100%, the description significantly enriches parameter meaning. It explains that filter is a substring match on metric names, that HELP/TYPE lines for matching metrics are retained, and that label values are NOT matched. For max_lines, it details the default (500) and the appended summary line, which the schema does not fully convey.

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 opens with a specific verb+resource: 'Get Prometheus metrics from Caddy.' It lists concrete metric categories (request counts, durations, TLS handshake stats, active connections) and clearly distinguishes this tool from sibling tools like caddy_config_get or caddy_status, which serve different purposes.

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?

The description provides clear guidance on when to use the filter and max_lines parameters, including examples and edge-case behavior (label values not matched). It does not explicitly contrast with alternatives, but among the siblings none offer metrics, so the context is clear enough for tool selection.

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