list_savepoints

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description's added value is the disclosure that storage paths are conditionally populated — a genuine output-behavior trait an agent would otherwise misread as a failure. It doesn't mention permissions, error behavior, or pagination, keeping it below 5.

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?

Two sentences, front-loaded with the resource scope and followed by the usage condition and caveat; no filler. The opening is a noun fragment rather than a full clause, a minor structural rough edge but not wasteful.

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 values needn't be explained, and the read-only annotations are sufficient for safety. What is missing is any parameter guidance for job_id/cluster, which matters for an open-world tool that may target multiple clusters.

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% for two parameters: the required job_id and the optional nullable cluster. The description never mentions either, nor explains what cluster selects or what the default (null) means — likely the configured/default cluster. For a 0%-coverage schema the description carries the full burden and largely drops it.

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 exact resources returned — savepoints, the latest completed checkpoint, and the restore source — each with storage paths, which is more specific than the bare name 'list_savepoints' and separates it from siblings like checkpoint_stats and job_details. The listing verb is only implied by the name rather than stated, but the resource scope is unambiguous.

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?

'Use it to find where a job can be restarted from' gives a concrete selection criterion, and the caveat that paths appear only for savepoints and for checkpoints retained on cancellation tells the agent when results will look empty. It does not explicitly name a sibling alternative or an exclusion, so it stops short of a 5.

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