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

The destructiveHint annotation is already present, but the description adds meaningful behavioral detail: only drafts awaiting release are affected, released and superseded versions remain untouched, and idempotence is guaranteed ('calling it again is harmless'). This goes beyond the annotation and clarifies exactly what the destructive operation destroys and what it preserves.

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 with the core action, then covers exclusions and idempotence. The German/English duplication doubles the length, but it is consistent wording and serves a bilingual audience, so the slight redundancy is acceptable.

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?

For a destructive tool with three parameters and no output schema, the description provides the essential call context: what is discarded, what is preserved, and that it is idempotent. The main omission is expected return or error behavior, but the described action and boundaries are sufficiently complete for an agent to invoke it safely.

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?

The schema already documents versionId and templateId, so the description adds little parameter-level meaning beyond restating the draft-discard concept. The reasoning parameter has no description in either the schema or the tool description, creating a small gap. At 67% schema coverage, the description is adequate but does not compensate for the undocumented reasoning field.

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 ('discards') and resource ('draft version') and adds the precise condition 'while it is still waiting for its release.' It also explicitly excludes released and superseded versions, which distinguishes it clearly from sibling tools like template_release and template_archive.

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 clearly states when the tool is applicable (draft pending release) and when it is not (released or superseded versions), plus notes that repeated calls are harmless. It does not name alternative sibling tools explicitly, but the when-not conditions provide enough routing guidance.

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