Resume Course Group Creation

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

Goes well beyond the annotations: discloses revalidation of memberships/ownership/permissions, all-or-nothing refusal of the remaining batch on conflict, single-use confirmation tokens where initial tokens never work, 24-hour/restart expiry, and explicit exclusions (no deletion, no moving students, no automatic rollback, no adoption of pre-existing objects). That is exactly the operational risk profile an agent needs for a destructive 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?

Front-loaded with purpose and the confirm-before-act pattern, then constraints and exclusions in short clauses; nearly every sentence carries distinct information. It is dense and long, but the density is justified for a destructive, multi-step operation.

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?

Output schema exists so return values need not be described, and the description covers permissions, expiry, conflict handling, irrecoverable IDs, and explicit non-behaviors. Nothing an agent needs to safely invoke this resume operation appears missing.

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 coverage is 0%, so the description must carry the load: it explains run_id's provenance and constraints (caller-owned, server-issued, scoped to one run, non-recoverable unknown IDs) and characterizes confirmation_token as a fresh single-use token, with null meaning no confirmation yet. Only minor gaps remain, e.g. the exact preview/confirm sequencing or token format.

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?

States a specific verb (resume) on a specific resource (pending work from a prior group creation run), and explicitly bounds scope to that run's recorded targets. An agent can distinguish this from create_course_groups because it operates on a prior run_id rather than fresh course/group IDs or CSV input.

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?

Clearly says what to pass (a caller-owned server-issued run_id) and what not to pass (course/group IDs or changed CSV), and notes a fresh preview plus single-use token is required. It never names the originating sibling tool (create_course_groups) explicitly, so the routing back to the creation step is implied rather than spelled out.

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