Api frameworks discard draft create

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

Annotations already declare destructiveHint=false and idempotentHint=false; the description adds real value by scoping the effect to the draft and stating that relational data is untouched. However it does not say whether the underlying published version is restored, what happens if no draft exists, or what authorization is required — gaps that matter for a mutation endpoint.

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?

A single seven-word sentence with the action front-loaded and no filler. It is efficiently sized, though the extreme brevity leaves the scope claim ('relational data') unexplained for a reader unfamiliar with the platform's draft model.

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 one-parameter endpoint with no output schema and annotations covering the safety profile, the description covers the core claim but omits the post-condition (does the framework revert to its published revision?), the identity of the referenced object, and error behavior when no draft is open.

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?

There is a single required parameter with 0% schema description coverage, and the description does not explain what 'id' refers to (framework id vs draft id). However, with only one required identifier passed alongside the framework-scoped tool name, the ambiguity is small and the description's statement about preserved relational data reduces the risk of mistaking it for a cascade delete.

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 names a specific verb (discard) and a specific resource/state (editing_draft), so an agent can tell it is a rollback of an in-progress edit rather than a delete of the framework itself. It does not differentiate this discard from the near-identical discard_draft endpoints on presets and risk_matrices, and it never says the draft belongs to a framework.

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?

There is no when-to-use guidance and no mention of the obvious alternatives in the sibling set (frameworks_publish_draft_create, frameworks_save_draft_partial_update, frameworks_start_editing_create). The agent must infer that this is the abort path of an editing session from the word 'discard' alone.

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