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

Annotations already declare readOnly, idempotent, non-destructive behavior. The description adds useful context beyond that: points are newest-first, expire after thirty days, carry an id, timestamp, and the tool that was about to run, and reason values have distinct semantics.

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 description is front-loaded with the resource and ordering, then explains reason semantics and expiry in three dense sentences. Every sentence carries useful information, though the middle sentence about assistant/restore points is slightly convoluted.

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 annotations covering safety and an output schema covering return shape, the description supplies the behavioral context an agent needs: ordering, expiry, and what each snapshot represents. It could be more explicit about when to call it, but the essential context is present.

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 only one parameter, and the schema already gives it 100% description coverage ('Catalog id, as returned by list_catalogs'). The description adds no parameter-specific meaning, so the baseline of 3 is appropriate.

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 states a specific resource (a catalog's restore points) and an ordering (newest first). It also explains the meaning of the reason values, which distinguishes this listing from generic catalog reads and makes the tool's role clear.

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 implied rather than stated explicitly: the description explains that the newest 'assistant' point is the pre-change state and that a 'restore' point undoes a restore, but it never says when to call list_catalog_snapshots versus restore_catalog_snapshot or other catalog tools. The agent can infer the workflow but has to do the work.

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