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

Annotations already mark destructiveHint=true and idempotentHint=true, and the description adds concrete behavioral detail: source_stage enables optimistic concurrency and returns 409 when stale. It also scopes what is destroyed (questions in a single draft round). This meaningfully supplements the structured annotations without contradicting them.

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?

Two terse sentences with no filler: the first front-loads the primary operation and inputs, the second adds the optional concurrency behavior. Every clause earns its place.

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 delete call, the description plus annotations give an agent enough to invoke it correctly: required ids and round_id, optional source_stage, and the 409 stale failure mode. There is no output schema, but the absence of a return description is acceptable here. The main minor gap is unspecified behavior for unknown or already-deleted ids.

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 description coverage is 0%, so the description carries the semantic burden. It clarifies that ids are question ids, round_id identifies the draft round, and source_stage uses the stage constant questions_and_directions plus a version for stale detection. The fixed action/resource fields are not explained, but the deletion-specific parameters are covered.

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 states the exact operation: 'Delete questions from one draft round by question id,' with a specific verb, resource scope, and identifier. This clearly distinguishes it from sibling tools like update_questions or delete_rounds. The action constant 'interview_plan.delete_questions' reinforces the purpose.

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 usage context is implied by the verb and scope ('one draft round'), so an agent can infer when to call it, but it does not explicitly name alternatives or when-not-to-use conditions. The source_stage note describes a concurrency detail rather than routing guidance. This is adequate but not explicit.

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