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

Beyond the annotations (which indicate a non-read-only, non-idempotent mutation), the description discloses key behaviors: published versions are immutable ('Published versions never change'), publishing the current draft does not freeze the draft ('keep iterating on the draft'), and any llmContext guidance in results should be followed. This is meaningful behavioral context that the annotations alone do not convey.

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 compact and front-loaded. The first sentence establishes the core purpose, the second adds the two key options (releaseType and config), and the final sentences cover immutability and result guidance. Every sentence earns its place with no filler or redundancy.

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?

Given the output schema exists and the input schema fully documents all six parameters, the description covers the remaining behavioral essentials: draft vs. published config, semver immutability, how releaseType works, and the llmContext instruction. An agent has enough information to decide when and how to call this tool correctly.

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%, so the baseline is 3. The description goes further by explaining the role of releaseType ('picks the major or minor bump') and the meaning of config ('publish that config instead of the draft'), which adds semantic clarity beyond the schema's property names. It does not repeat every parameter, but the schema already documents them fully.

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 action ('publish the splitter's current draft config'), the output ('new immutable semver version'), and the purpose ('runs and evaluations can pin'), which clearly distinguishes it from siblings like publish_classifier_version and publish_extractor_version. The splitter-specific context and draft-to-version flow make the tool's identity 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?

The description provides clear context for when to use the tool: when you need an immutable, pinnable splitter version. It also hints at the alternative workflow ('keep iterating on the draft') and explains the config override path. It does not explicitly name alternative tools such as update_splitter or publish_classifier_version, but the usage context is clear enough to steer an agent correctly.

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