remove_submission

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description goes well beyond them: it specifies exactly what is destroyed (submitted files/text, not drafts), that the effect is irreversible, and — unusually valuable — that dry_run=False is currently broken by a known upstream 'invalid parameter' error while dry_run=True is safe. That is exactly the kind of operational caveat annotations cannot carry.

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 action and the irreversibility warning, then the known issue, then the confirmation protocol — a sensible priority order. Slightly redundant, since the dry_run confirmation flow is restated in both prose and the schema's dry_run description, but every paragraph carries distinct information.

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 no explanation, and the description covers the remaining risk surface: destructive scope, irreversibility, a known upstream failure mode, and the required confirmation workflow. Nothing an agent needs before calling this destructive tool 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?

Schema coverage is 100%, so the baseline is 3; the description adds real value by framing dry_run as a two-phase preview/commit workflow ('same parameters') rather than a simple boolean, and by warning that the commit phase currently fails. It does not add anything for course_id/assignment_id, but the schema already covers those with sourcing hints.

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 ('withdraw/clear this account's own submission for an assignment') and immediately scopes it against a likely confusion point: 'not a draft' and 'already-submitted work'. It also distinguishes itself from the related remove_submission_for tool, so an agent can tell what this does without opening the schema.

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?

Gives an explicit operating protocol: call with dry_run=True first, show the preview to the user, then call again with dry_run=False only after explicit confirmation. It also names the alternative path (remove_submission_for) for the case this tool cannot handle.

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