Publish Recipe Draft

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

Annotations already signal idempotency, open-world behavior, and non-read-only semantics, and the description adds substantial context: immutable revisions, atomic batch publication, snapshot compilation, frozen MMM priors on capable backends, VAR evidence requirements, invalid-calibration failure, and preservation of disabled observations. No contradiction with annotations was found.

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 core purpose is front-loaded and most caveats are relevant, but the description is a dense block of domain warnings and includes an unclear fragment ('Does not fit, consume an attempt or designate a champion'). It is compact but not cleanly structured or fully readable.

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 openWorldHint and the tool's complexity, the description does cover backend-capability differences, idempotent replay, atomicity, and MMM/VAR-specific constraints. However, required parameters like expected_version and reason remain unexplained, and the garbled exclusion sentence adds ambiguity, so the description is not complete on its own.

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?

With 0% schema description coverage, the description must explain the required parameters, but it only gives real semantics to publication_id ('new UUID', reuse after uncertain response) and only implicitly refers to the saved draft. The roles of expected_version and reason are not explained at all.

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 first sentence clearly states the action and resource: publishing a saved MMM or VAR draft as immutable recipe revisions. This distinguishes it from draft creation/update tools, though it does not explicitly name sibling tools, and the later sentence 'Does not fit, consume an attempt or designate a champion' is garbled and weakens precision.

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 gives useful context for when to use the tool: saved drafts, idempotent retry with the same publication_id, never sending separately prepared settings, and checking backend capabilities. It does not explicitly name alternatives or state when not to use this tool, and the exclusion phrase is unclear.

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