PLATO MCP

remove_submission

Destructive

Withdraw/clear this account's own submission for an assignment. IRREVERSIBLE and DESTRUCTIVE once dry_run=False -- this discards already-submitted work (files/text), not a draft.

    KNOWN ISSUE: live testing found dry_run=False currently fails with
    an "invalid parameter" error from PLATO every time (the real
    required parameter shape wasn't determined -- see
    remove_submission_for's docstring). dry_run=True (preview) works
    and is safe to call. Do not rely on dry_run=False actually working
    until this is fixed.

    Call with dry_run=True (default) first, show the preview to the user,
    and only call again with dry_run=False after they explicitly confirm.

Input Schema

Name	Required	Description
`dry_run`	No	If True (default), only preview the removal without doing it. Call again with dry_run=False (same parameters) to actually remove it.
`course_id`	Yes	PLATO/Moodle numeric course id, e.g. from list_courses.
`assignment_id`	Yes	Assignment id, e.g. from list_assignments.

Output Schema

Name	Required	Description	Default
`dry_run`	Yes
`message`	Yes
`preview`	Yes
`executed`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 28, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing irreversibility, that it discards already-submitted files/text rather than a draft, and a known live-testing failure of dry_run=False. That last item is exactly the kind of runtime behavior an annotation cannot carry and materially changes how an agent should call the tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence front-loads the action, and the safety/confirmation instructions follow in order of importance. The KNOWN ISSUE block is a bit long, but every sentence there changes agent behavior, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive tool with an output schema already covering return values, the description supplies the missing pieces: safety protocol, what exactly gets destroyed, and the current unreliability of the non-preview path. Nothing an agent needs to act correctly is absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 100%, so this dimension is baseline-driven, but the description adds real semantic value by framing dry_run as a mandatory preview-then-confirm workflow rather than a passive flag. It does not add anything about course_id/assignment_id beyond what the schema states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb pair ('withdraw/clear') and a precise resource ('this account's own submission for an assignment'), and explicitly excludes drafts. An agent can distinguish this from submit_assignment and remove_submission_for without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit two-step protocol: call with dry_run=True, show the preview, get explicit user confirmation, then call again with dry_run=False. It also states when NOT to rely on the tool (dry_run=False is currently broken) and points at remove_submission_for for the real parameter shape.

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

All PLATO MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.