discard_staged

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

With no annotations, the description carries the full burden. It does add one genuinely useful piece of context – 'Does not touch Canvas', i.e. the operation is local to staging and has no external side effect – but it omits reversibility, behavior when nothing is staged, and error conditions for a destructive tool.

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 short sentences, zero waste, with the destructive scope front-loaded and the side-effect boundary stated immediately after. Nothing needs trimming or reordering.

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 values need not be described, and the tool is a simple scoped delete. The main remaining gap is the absence of any error/edge-case behavior for a destructive operation with no annotations to fall back on.

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. It explains user_ids semantics ('all for the assignment, or only the given students'), which is the one non-obvious parameter, but gives no format or validation detail for course_id/assignment_id.

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 gives a specific verb+resource ('Delete staged grades') and clarifies the two deletion scopes (whole assignment vs. only given students), which cleanly separates it from siblings like post_staged_grades and stage_grade. It doesn't explicitly name those siblings, so it falls short of the top tier.

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?

Usage is only implied: an agent infers you call this when you want to undo staging. No when-not guidance and no explicit pointer to the alternative (post_staged_grades for committing), so the agent must reason about intent from the sibling list.

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