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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds state-machine semantics beyond that: the terminal states and what accompanies each (courseId on success, error on failure), which is genuinely useful for a polling tool. No rate-limit or backoff guidance, but the key behavioral trait is disclosed.

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 tight sentences with the primary action front-loaded and the polling instruction immediately after. No filler, 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?

An output schema exists, so return-value documentation is not required, yet the description usefully notes the terminal states an agent will observe. Combined with annotations covering safety and a fully documented single parameter, it is nearly complete; only polling cadence is left implicit.

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 100% and the schema itself explains the id comes from generate_course. The description adds no additional parameter syntax or constraints. Baseline 3 is appropriate when the schema carries full responsibility.

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 and resource ('Fetches a generation job') and frames it as the async counterpart to generate_course. An agent can tell what it does at a glance, though it does not explicitly distinguish itself from sibling get_* tools beyond the generation-job framing.

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?

Gives clear operational guidance: poll until status is completed or failed. This tells the agent the calling pattern (repeated polling) and the terminal conditions. It stops short of naming any alternative tool or stating a polling interval, but the workflow context is explicit enough to act on.

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