Node Latency

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. Beyond that, the description adds genuine operational context: LATENCY LATEST only yields data when latency-monitor-threshold is configured, HISTOGRAM requires Redis 7+/Valkey, and the response includes heavy-tail findings. It stops short of saying what happens when monitoring is disabled (empty result versus error).

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 definition is a single dense sentence that front-loads the three measurement sources and keeps the qualification conditions in tight parentheticals. It is jargon-heavy but every clause carries information; the only mild cost is that the conditional prerequisites are buried mid-sentence rather than separated.

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?

An output schema exists, so return-shape explanation is unnecessary, and the read-only annotations remove the need for mutation caveats. The prerequisites and version gating are present, which is the main thing an agent needs before calling; the remaining gap is the undocumented ping_samples parameter and the unstated behavior when the latency monitor is off.

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?

There is one parameter, ping_samples (default 20, range 1-500), and the schema has 0% description coverage, so the description carries the full burden of explaining it. The description never mentions sampling at all, leaving the agent to guess what ping_samples controls, how it affects cost/runtime, or whether a higher value is needed for stable percentiles.

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 the concrete data sources it reports on (client PING RTT percentiles, LATENCY LATEST events, LATENCY HISTOGRAM per-command p50/p99/p99.9) plus a derived output ('findings for heavy tails'), so an agent knows this is a latency-metrics collector. It is a noun-phrase inventory rather than a verb, and it does not explicitly separate itself from the sibling node_latency_events, which overlaps on the 'LATENCY LATEST events' portion.

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?

Usage is only implied: the described metrics signal a latency-diagnosis scenario, and the parenthetical 'needs latency-monitor-threshold > 0' plus the Redis 7+/Valkey note are real preconditions an agent must check before calling. There is no explicit when-to-use versus when-not, and no named alternative such as node_latency_events for an events-only query.

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