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

Annotations already establish read-only, idempotent, non-destructive behavior. The description adds useful context beyond that: versions are immutable and published, hasMore signals remaining items, and pagination should be avoided unless necessary. No contradiction with annotations.

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 two sentences with no filler: it front-loads the core purpose, then packs the alternative tool and pagination policy. Every clause earns its place.

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 full schema coverage, a present output schema, and strong safety annotations, the necessary call information is covered. The description completes the picture by noting version immutability and pagination behavior, leaving no major gap for an agent deciding how to call it.

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 coverage is 100% with detailed parameter descriptions, so the baseline is 3. The description adds extra meaning for nextPageToken usage and the hasMore response signal. However, the phrase 'narrowing filters' is vague because the schema exposes no explicit filter parameters beyond the required identifiers.

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 the exact action and resource: 'List a splitter's published (immutable) versions.' It also distinguishes itself from get_splitter by pointing to that tool for fetching a single version's config, so an agent can tell list behavior from fetch behavior.

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 explicitly names get_splitter as the alternative when one version's config is needed and provides concrete pagination rules: prefer narrowing filters over paginating, and pass nextPageToken only when every item is needed. This is actionable when-to/not-to guidance.

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