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

Annotations already indicate readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=true. The description adds meaningful behavioral context: published versions are immutable ('Published versions never change'), releaseType picks the bump, and passing config publishes that config instead of the draft. This goes beyond the annotations and helps the agent understand side effects and constraints. It doesn't mention permissions or rate limits, but the schema already covers environment/workspace grants, so the description's added value is solid.

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, front-loaded with the core action and outcome, and every clause earns its place. It packs the immutability warning, the releaseType behavior, the config override, and the draft-iteration guidance into a compact, readable form. No filler or repetition of schema details.

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?

The tool has an output schema, so return values are already documented. The description covers the key behavioral aspects: what gets published, how releaseType works, the config override, and immutability. It doesn't explicitly state what happens to existing pinned versions or whether publishing requires a prior draft, but the draft-centric language and the output schema cover most of what an agent needs. A small gap is not mentioning that the draft remains editable after publishing, though 'keep iterating on the draft' implies 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 description coverage is 100%, so the schema already documents all six parameters. The description adds a little extra meaning by explaining the relationship between releaseType and semver bumping, and by clarifying that config overrides the draft. However, it doesn't add much beyond the schema's own descriptions, so a baseline 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 verb ('Publish'), a resource ('splitter's current draft config'), and the result ('a new immutable semver version'). It also distinguishes the tool from siblings like publish_classifier_version and publish_extractor_version by naming the splitter resource and the draft-to-version flow. The title reinforces the same message, and the description adds the key immutability trait that makes the purpose unmistakable.

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 explains when to use this tool: when you want to pin a splitter config for runs and evaluations, and it notes that you should keep iterating on the draft after publishing. It does not explicitly name alternatives or exclusions, but the context of sibling tools (publish_classifier_version, publish_extractor_version) and the splitter-specific language make the usage context clear. A small gap is that it doesn't say 'use update_splitter to modify the draft instead' explicitly, but the draft iteration guidance implies it.

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