waver_latency

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

Beyond the readOnlyHint annotation, it discloses the half-open [start, end) range, the pairing rule (first B edge at or after each A edge), and the exact statistics returned (min/max/mean/p50/stddev plus first/last pairs). It also warns about the binary-signal requirement for rising-edge mode, an otherwise unstated failure condition.

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?

Five short sentences deliver the metric, algorithm, output statistics, edge-mode caveat, time format, and sibling alternative without wasted words. The definition is front-loaded with the core question and then adds necessary detail.

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 an output schema present, the description covers the remaining needed guidance: selection criteria, algorithm, statistical outputs, constraints, and when to use an alternative. The unstated file semantics are a minor shared convention and do not block correct invocation.

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 0%, so the description must supply meaning for a, b, edge, start, and end; it does, including time formats and edge-mode constraints. However, the file parameter is left implicit and the meaning of null end is not stated, so it does not fully compensate for all six parameters.

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 opening question and restatement define the exact metric: propagation delay from an edge of signal A to the corresponding edge of signal B. It also distinguishes itself from waver_analyze by explicitly noting that the sibling is for one signal's own timing.

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?

It lists the natural-language queries this tool answers and explicitly routes single-signal timing questions to waver_analyze. It also gives conditional guidance for edge='rise' (binary signals only) vs edge='any' (any change), telling the agent when each mode is appropriate.

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