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

Annotations only convey destructiveHint and idempotentHint, but the description adds valuable behavioral detail: rounds updated in place keep their id and preserve questions/directions, order must be a complete permutation, and source_stage returns 409 when stale. This meaningfully qualifies the destructive hint and exposes concurrency behavior.

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 sentences with no filler. The core operation is front-loaded, then the most important behavioral consequences (preservation, determinism, stale check) follow compactly. Every sentence 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?

Given the absence of an output schema and low schema coverage, the description covers the major pitfalls: replacement semantics, ordering constraints, child-data preservation, and optimistic concurrency. It does not explicitly state the return value or whether at least one of items/order is required, but the 'and/or' phrasing and schema structure partially address this.

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 carries the burden of explaining parameters, and it compensates well for the trickiest ones: id ('by id'), order ('complete permutation of resulting ids'), and source_stage ('returns 409 when stale'). It does not explain the many item subfields or the action/resource wrapper, but those are largely self-evident or constrained by the schema.

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 opens with a specific verb and resource: 'Replace draft interview rounds by id and/or reorder them with order', making the tool's function immediately clear. It also distinguishes itself from sibling generation tools with 'deterministic, no AI generation', so an agent can tell this apart from generate_rounds.

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 clear context for use: deterministic editing and reordering rather than AI generation, and it notes that updating in place preserves questions and directions – implying this is preferable to delete-and-recreate flows. However, it does not explicitly name sibling alternatives like add_rounds or delete_rounds or state when-not-to-use conditions.

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