job_timeline

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

Beyond the read-only/idempotent annotations, the description discloses genuinely non-obvious behavior: Flink keeps no event log so coverage limits are reported, unreadable sources are surfaced, and a restart appears only when a recorded failure or restore proves it. The truncation rule ("keeps the most recent `limit` events") also matters. It stops short of describing output shape, but the output schema covers that.

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?

Purpose is front-loaded in the first clause with the event inventory following, and no sentence is filler. It is dense to the point of being slightly run-on across four sentences, but every clause carries behavioral information.

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 and annotations covering the safety profile, the description focuses correctly on provenance and coverage limits for an open-world tool. The remaining gap is the unexplained `cluster` parameter, which determines whether the Kubernetes event sources are even reachable.

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% across three parameters, so the description carries the full burden. It explains `limit` only implicitly ("most recent `limit` events"), and says nothing about what `job_id` accepts or, more importantly, what `cluster` does or when it should be supplied for the Kubernetes event path.

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 concretely enumerates what the timeline contains (state entries, exceptions, checkpoints, savepoints/restores, k8s operator/pod events) and its ordering (oldest first), which clearly distinguishes it as an aggregated post-mortem view. It doesn't explicitly name how it relates to close siblings like `job_exceptions` or `checkpoint_stats`, so an agent must infer whether this supersedes or complements them.

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?

"What happened to a job and when" implies post-mortem/debugging usage, but there is no explicit when-to-use statement, no exclusion criteria, and no routing to alternatives such as `diagnose_job` or `job_exceptions`. The `coverage` caveat hints at when the result will be incomplete, which is useful, but the usage decision itself is left implicit.

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