get_courses_enrollments_user

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

Adds substantial behavior beyond the annotations: auth is injected server-side and 'never by the model', calls are throttled under LearnWorlds' 30-per-10s cap and retried on 429/5xx, and non-2xx replies surface with status plus 401/403/404/422 meanings. None of this contradicts readOnlyHint, idempotentHint, openWorldHint, or destructiveHint=false.

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 the READ-ONLY marker, endpoint, and core behavior, then organized into labeled Behavior/Parameters/Returns/Use-when sections. Each section earns its place; the only mild redundancy is 'creates, changes and deletes nothing' mirroring the annotations, which works as a safety cue rather than waste.

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?

Very complete for a 2-parameter read-only tool with no output schema: it covers return shape, error payloads, auth, rate limits, retries, and usage routing. The remaining gaps are minor — no field-level enumeration of what 'course enrollment data' contains, and no explicit disambiguation from get_users_per_course.

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% so the baseline is 3, but the description contributes operational param guidance the schema lacks: the 50-enrollments-per-page limit and the instruction to walk results with `page`. This tells the agent how many paged calls may be required, which is genuinely additive.

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 — 'Get courses (enrollments) of user' — with explicit user scoping and the HTTP endpoint GET /v2/users/{id}/courses. The pagination detail (50 per page) further pins down the return shape. This is unambiguous against siblings like get_courses or the inverse get_users_per_course.

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?

Explicitly gives when-to-use ('safe to call speculatively for lookups and reporting') and when-not ('Not for changing anything — use the matching 🟡 write tool'). It names related Users tools but without selection conditions among them, so an agent must still infer which specific lookup fits a given need.

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