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

The annotations provide the safety profile (readOnly=false, openWorld=true, idempotent=false, destructive=false), while the description adds important non-obvious behavior: published versions never change, the default source is the current draft, and config can override the draft. This goes beyond what the annotations alone signal.

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?

Three sentences front-load the core purpose and the immutability guarantee. There is slight redundancy between 'immutable semver version' and 'Published versions never change', but it is acceptable emphasis and every sentence contributes useful information.

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 rich schema (100% parameter coverage, output schema, enums) and annotations, the description covers the remaining contextual needs: why to publish, what happens to the draft, and the releaseType/config behavior. Nothing essential for correct invocation is missing.

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 that releaseType selects the major/minor bump and that passing config publishes that config instead of the draft. This adds meaning beyond the schema's enum and property descriptions.

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 clear resource ('the extractor's current draft config') and defines the output as an immutable semver version. It distinguishes this from update-style tools by emphasizing that published versions are immutable and can be pinned by runs and evaluations.

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 conveys when to use it: to turn a draft into a stable, pin-able version and to continue iterating on the draft after publishing. It does not explicitly name sibling alternatives like update_extractor or publish_classifier_version, but the 'extract group' cue and immutable-version framing make the intended context clear without exclusions.

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