submit_artifactSubmit a lab deliverable. Stores it in the learner's Library (type='deliverable') and returns the module rubric so it can be reviewed against the bar. Call get_review next. For general note-taking use save_artifact instead.
| Name | Required | Description | Default |
|---|---|---|---|
| type | Yes | ||
| course | Yes | ||
| module | Yes | ||
| repo_ref | No | ||
| auth_token | No | ||
| content_text | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only cover destructiveHint=false, so the description adds meaningful behavioral context: it stores content in the Library with type='deliverable' and returns the module rubric. It also discloses the workflow expectation to call get_review next. It stops short of covering auth requirements or failure modes, but it goes well beyond the minimal annotation coverage.
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?
The description is three sentences with no filler. The first sentence states purpose, the second explains the side effect and return, and the third gives workflow and alternative. It is front-loaded and every sentence 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?
The description is strong on purpose, workflow, and alternative, and the output schema covers return values. However, with 6 parameters and all schema descriptions absent, the lack of parameter-level guidance leaves a notable gap. The description is sufficient for selection but not fully complete for reliable invocation without further inference.
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 description coverage is 0%, so the description must compensate for undocumented parameters. It only clarifies that type is set to 'deliverable' and vaguely references a module rubric, but it does not explain the required course/module parameters or the optional repo_ref, auth_token, and content_text. This leaves significant ambiguity for invocation.
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 opens with a specific verb and resource ('Submit a lab deliverable'), then clarifies the unique behavior: stores as type='deliverable' in the learner's Library and returns the module rubric. It also distinguishes itself from note-taking via the save_artifact alternative, making it clearly different from siblings like get_artifact and list_artifacts.
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 explicitly states the follow-up action ('Call get_review next') and provides an explicit alternative for when not to use this tool ('For general note-taking use save_artifact instead'). This gives the agent clear when-to-use and when-not-to-use guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools have clearly distinct purposes, but a few overlap or share boundaries: get_lesson vs teach_section (lesson vs section), recall_questions vs daily_drill (both spaced recall), and get_recap vs get_progress (both progress summaries). Descriptions generally help, but these pairs could cause misselection.
The vast majority follow a verb_noun snake_case pattern (get_outline, begin_course, submit_exam, etc.). Minor deviations include daily_drill (adjective_noun), interview_prep (noun_noun), login, roast, and whoami (single words), but the overall style is consistent and readable.
24 tools is on the heavy side (16-25 feels bloated), though the platform spans courses, exams, interviews, artifacts, and user management, so the breadth is defensible. Some tools could be consolidated (e.g., recall_questions and daily_drill), making it feel slightly over-scoped.
Core learner workflows are covered: discover, start, learn, assess, track, and resume. However, descriptions reference missing tools like get_review and save_artifact, creating dead ends. There's also no tool for authoring/managing courses, even though list_courses mentions user-authored courses, leaving notable gaps.