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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description only needs to add contextual behavior. It does: it reveals the polling contract and the terminal statuses (completed with courseId, failed with error), plus the plan requirement. This goes beyond what annotations provide, without contradiction.

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: the first states the core action, the second packs the polling behavior and a requirement. Every word earns its place, and the most critical information (what to poll for) is front-loaded. No redundancy or filler.

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?

The tool is simple (one parameter) and has an output schema, so the description needn't detail return values. It covers the essential usage pattern and requirements. The only minor gap is that it doesn't mention timeout or retry behavior, but that's not typically required for such a poll-and-check tool; otherwise it is complete.

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?

There is only one parameter, 'id', and the schema already documents it as 'The generation job id returned by generate_course' at 100% coverage. The description does not add any additional meaning about the parameter itself, so the baseline of 3 applies.

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 verb ('Fetches') and resource ('generation job'), clearly distinguishing it from the many other get_* tools like get_course or get_theme. The polling semantics also make it unambiguous that this is the status-check tool for asynchronous generation.

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 explains the intended usage pattern: poll until 'completed' or 'failed', which implicitly tells when to call it (after generate_course) and how to interpret results. It also notes the plan requirement, a key prerequisite. However, it does not explicitly name an alternative or state when not to use it, so it misses the top tier.

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