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

Beyond the annotations' destructiveHint and idempotentHint, the description discloses that deleting a round also prunes its questions and directions in the same write, that pruned ids are reported, and that stale versioned edits return 409. This is exactly the behavioral context an agent needs before invoking a destructive draft mutation.

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 short sentences present the action first, then side effects and invariants, then the optional concurrency parameter. Every clause adds semantic information; there is no repetition of the title or schema.

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 no output schema, it covers what gets deleted, what side effects occur, the minimum-remaining-round invariant, and the stale-write error. The only notable omission is a fuller description of the success response shape beyond "reports the pruned ids", which prevents a top 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?

It translates the opaque ids and source_stage objects into meaning: ids identify draft rounds to delete, and source_stage is a concurrency guard with stage interview_sequence and version that triggers 409 when stale. With zero schema descriptions, this compensation is valuable, though generic top-level fields are left to schema conventions.

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 opening clause "Delete draft interview rounds by id" names a specific verb, resource, and targeting method, distinguishing it from sibling delete_* tools that act on anchors, competencies, questions, or skills. The cascade behavior further clarifies it is about rounds, not the child content individually.

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 gives practical context—the sequence must keep at least one round, and passing source_stage adds optimistic concurrency with a 409 on staleness—so an agent knows preconditions and when the 409 path matters. However, it never explicitly routes between this and sibling tools such as delete_questions or delete_anchors, leaving alternatives to be inferred from names.

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