get_metrics

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

Annotations declare readOnlyHint=true and idempotentHint=true, but the tool exposes a drain_spool action returning 'drained entry counts' — draining consumes/removes spool entries, which is a state mutation and is not idempotent. The description thus contradicts the read-only/idempotent safety profile for at least one action, and it never warns that one action differs in side effects from the rest.

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-loads the resource list, then routes to the alternative, then summarizes returns — a sensible order. The 'Returns telemetry metrics...' sentence largely re-states the opening list, and the action enum is repeated from the schema, adding minor redundancy.

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 7-param, 6-mode read/mutate hybrid with no output schema, the description does cover purpose, alternatives, and return categories. However it fails to disambiguate the side-effect profile across actions (drain_spool vs read-only modes), which is exactly the information an agent needs before invoking, so it is adequate but with a material gap.

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 every parameter is already documented, and the description merely repeats the action enum verbatim. It adds no syntax, format, or meaning (e.g., how trace_id interacts with execution_id filter, or what behavior_name expects) beyond the schema, matching the 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 (Retrieve) plus the concrete resource set: runtime telemetry, tick durations, stuck events, category statistics, and 60Hz action outcome spool entries. It also names the sibling it differs from (get_status) and the axis of difference (performance/spooled outcomes vs active node traversal), so an agent can separate the two without opening either 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?

Contains an explicit when-to-use/when-not clause: 'Use get_metrics instead of get_status when evaluating tick performance, reading spooled action outcomes, or inspecting aggregated statistics rather than active node traversal.' The alternative tool and the selecting condition are both named.

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