adaptorch_server_metrics

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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine value beyond that by disclosing that counters are "redacted" and that latency is expressed as percentiles, which affects how results should be interpreted. It stops short of saying what time window or aggregation scope the counters cover, which matters for a no-parameter metrics endpoint.

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 sentence with no filler, and the key qualifiers ("redacted", "latency percentiles") are front-loaded. Nothing to trim and nothing repeated from the annotations.

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 the return value, and it only names the two metric families without indicating shape, window, or units. For a simple read-only metrics call this is minimally adequate, but an agent cannot predict whether counters are cumulative, per-window, or per-tool without invoking it.

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 no parameter semantics to document; the schema and description are consistent on that point. Baseline of 4 applies for a parameterless 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?

States a specific verb ("Return") and a specific resource ("MCP tool-call counters and latency percentiles"), which is enough to separate it from run/artifact management siblings. It does not explicitly differentiate itself from the closest sibling, adaptorch_usage, which likely also returns usage 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 explicit when-to-use or when-not-to-use guidance, and no alternative is named. Usage is only implied by the description (call this when you need tool-call metrics), leaving the agent to guess how it differs from adaptorch_usage or adaptorch_capabilities.

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