mark_as_complete

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

Beyond the annotations, the description discloses non-idempotency consequences (duplicate effects on repeated calls), server-side auth injection (the model must never supply auth), throttling under LearnWorlds' 30-per-10s cap with retries on 429/5xx, and full error-code semantics for 401/403/404/422. These details directly shape agent behavior and are not derivable from annotations or the schema.

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 long, but every labeled section (Behavior, Parameters, Returns, Use when) carries essential information for a mutation tool with no output schema. It is front-loaded with the WRITE status, endpoint, and non-idempotency warning before descending into detail; only minor trimming would be possible.

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?

Since there is no output schema, the description fully explains return values (HTTP status followed by the JSON response body) and how errors surface as tool errors with status and API payload. Combined with the body-parameter caveat, auth/throttling notes, and usage pre-checks, there are no material gaps for an agent to invoke this tool correctly.

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 id, cid, units, and send_course_complete_email are already well documented. The description adds one critical clarification: the entire payload goes in the single body argument forwarded verbatim, and although the spec marks body optional, this endpoint expects one — a caveat that prevents a foreseeable agent failure when following the schema naively.

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 and resource: 'Updates the user's progress on a course or learning activity level as complete.' It clearly frames the operation as a WRITE action with the exact endpoint, and naming reset_user_progress as the related sibling makes its scope unmistakable even within the large sibling set.

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 'Use when' section is explicitly prescriptive: use only when the user asked to create this, and first verify with a 🟢 read tool that the target exists and the record is not already there. It also points to reset_user_progress as the related alternative, giving the agent clear routing guidance between the two progress-mutation tools.

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