start_course_sync

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

Annotations indicate this is a mutating, idempotent, non-destructive operation. The description adds critical behavioral context by stating the job runs in the background and is batch-bounded, and by directing the agent to a polling loop for continuation. This goes beyond what annotations alone provide.

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 sentences deliver the core action, the bounded scope, and the follow-up workflow. Every clause earns its place, and the most important information is front-loaded.

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?

With no output schema, the description wisely avoids promising a return value and instead tells the agent what to do next: poll get_sync_status. It covers the asynchronous nature, batch limit, and continuation mechanism. It is slightly thin on exact return behavior, but the provided workflow makes the tool usable.

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 only 33%, so the description must compensate. It indirectly explains maxFiles through 'bounded batch of lecture files' and startAt through the nextStartAt batching pattern, but it never explicitly maps these concepts to the parameter names. The added context is helpful but incomplete.

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 a specific action ('Start a background index job') and a clear resource scope: course outline, announcements, assignments, and a bounded batch of lecture files. It distinguishes itself from the polling tool get_sync_status by framing itself as the initiating action.

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 operational guidance: after starting, poll get_sync_status and use nextStartAt for subsequent batches. It does not explicitly list exclusion conditions or compare against tools like clear_local_index, but the workflow context is strong enough for an agent to know when to invoke it.

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