reset_user_progress

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

The description goes far beyond the annotations, explaining non-idempotency in concrete terms ('a repeated call can duplicate the effect'), server-side auth injection, throttling under the 30-per-10s cap, retries on 429/5xx, and the exact error-payload semantics for non-2xx replies. This is rich, actionable behavioral context that annotations alone do not provide.

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 well-structured with labeled sections (Behavior, Parameters, Returns, Use when) and front-loaded with the WRITE status and endpoint. It is somewhat verbose but every section earns its place. There is a small redundancy between 'creates data' in the header and 'creates a record or triggers an action' in the Behavior section.

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?

For a mutating, non-idempotent tool with no output schema, the description covers essentially everything needed: endpoint, HTTP method, auth, rate limiting, retry behavior, return format, error codes, preconditions, and a related sibling. No critical information for correct invocation is missing.

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?

The schema already covers all three parameters (100% coverage), so the baseline is 3. The description adds important value by clarifying that the full JSON payload goes in the single body argument, is forwarded verbatim, and that while the spec marks body optional, this endpoint actually expects one. It doesn't expand on id/cid beyond their schema descriptions, which is acceptable given the coverage.

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: 'Resets the user's progress on a course or learning activity level,' which matches the tool name and endpoint. The action is unambiguous even without sibling comparison. A minor flaw is the 'Use when: only when the user asked to create this' phrase, which uses 'create' instead of 'reset' and slightly muddies the intended trigger.

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?

Provides an explicit 'Use when' section: invoke only on explicit user request, verify existence with a 🟢 read tool first, and names mark_as_complete as the related progress-update tool. This gives a clear decision path, though it could be stronger by explicitly stating 'use mark_as_complete for completion requests' instead of just calling it 'related.'

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