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

The annotations provide only basic flags (readOnlyHint=false, idempotentHint=false, destructiveHint=false), so the description adds meaningful behavioral context: published versions never change, releaseType drives the bump, and a config can be passed to publish that config instead of the draft. This goes beyond the structured annotations and does not contradict them.

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 efficient: three sentences front-load the core publishing behavior, then add releaseType, config override, and immutability guidance. The parenthetical '(extract group)' and the 'llmContext guidance' sentence are slightly opaque, but they do not cause significant bloat or confusion.

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 tool has an output schema and a detailed input schema, the description does not need to explain return values or every parameter. It covers the central immutable-version semantics, the draft workflow, and the release-type behavior. Minor ambiguity around 'extract group' and the llmContext instruction prevents a perfect score.

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 the parameters thoroughly. The description adds little beyond restating what releaseType and config do, which is already in the schema. This is a baseline-3 situation where the schema handles the heavy lifting.

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 uses a specific verb ('Publish') and a specific resource ('the extractor's current draft config as a new immutable semver version'), and it clearly distinguishes this from sibling tools like publish_classifier_version and publish_splitter_version by scoping it to extractors. It also adds the key semantic that published versions are immutable, so it is far from a tautology.

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 makes the use case clear: publish versions so runs and evaluations can pin them, and keep iterating on the draft instead of changing published versions. It implies the workflow and says when to use the tool, though it does not explicitly name alternatives or state when-not-to-use conditions, so it stops short of perfect guidance.

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