Skip to main content
Glama
MD MCP Plugin

MD MCP Plugin

by yanling37

md_recover_curve_operation

Recovers a curve operation that left a partial target by reloading the saved project and discarding unsaved changes; keeps the original failure receipt and never repeats the curve write.

Instructions

Reload the same saved project after a known-complete curve input batch left a partial target. Discards its unsaved project changes. Requires unchanged native readback, closed input, the saved-file SHA and ownership of the unresolved lease. Keeps the original failure receipt; never repeats the curve write.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "blocked_request_id": "<blocked_request_id>",
      "request_id": "<request_id>",
      "scene_token": "<scene_token>",
      "expected_source_sha256": "<expected_source_sha256>"
    },
    "name": "md_recover_curve_operation"
  }
}

Input Schema

NameRequiredDescriptionDefault
request_idYes
scene_tokenYes
blocked_request_idYes
expected_source_sha256Yes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior5/5

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

With no annotations supplied, the description carries the full burden and does so: it discloses a destructive effect ("Discards its unsaved project changes"), four hard preconditions, and the idempotency guarantee ("Keeps the original failure receipt; never repeats the curve write"). An agent knows the blast radius and failure semantics before invoking.

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?

Three tight sentences with the destructive effect front-loaded immediately after the purpose. The compression occasionally costs clarity — "Requires unchanged native readback, closed input" is telegraphic — but no sentence is filler.

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

Completeness4/5

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

For an unannotated, destructive recovery operation with no output schema, the description covers purpose, precondition set, side effects, and idempotency, which is most of what matters. It omits what the tool returns or how precondition failures surface, leaving a small gap for a recovery tool where the caller must react to outcomes.

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

Parameters2/5

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

Schema description coverage is 0% across four required parameters, so the description must compensate and largely fails to. "The saved-file SHA" plausibly maps to expected_source_sha256, but request_id, scene_token, and blocked_request_id are never explained, nor is the relationship between the lease ownership and the blocked request.

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

Purpose4/5

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

States a specific verb and resource ("Reload the same saved project") plus the exact triggering condition ("known-complete curve input batch left a partial target"), which distinguishes it in spirit from the cut-recovery sibling by naming the curve scenario. It stops short of explicitly contrasting itself with any named alternative, so it is clear but not sibling-differentiated by name.

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

Usage Guidelines3/5

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

The trigger condition is stated (a partial target after a complete curve input batch), which strongly implies when to call this. However there are no explicit exclusions, no named alternative tool, and no guidance on what to do when the preconditions (unchanged readback, closed input, lease ownership) are not met.

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

Deploy Server

Other Tools