anki-workflow-mcp

Overview Schema Source Related Servers Discussions Admin

Manifesto Commit

manifesto_commit

Commits a validated Anki flashcard batch transactionally using a receipt hash, registering IDs, topics, tags, changelog entries, and queue updates only after QA and cloze checks pass.

Instructions

Sole writer of the Manifesto. Commits a batch's data transactionally. Requires a valid receipt (content_hash from validate_batch PASS). Parameters: deck_dir, batch_id, receipt_hash, qa_csv, cloze_csv (for receipt verification), new_ids (JSON array of IDEntry dicts), new_topics (JSON array of strings), new_tags (comma-separated), changelog_entries (JSON array), queue_updates (JSON array of strings to add).

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": {
      "deck_dir": "<deck_dir>",
      "batch_id": "<batch_id>",
      "receipt_hash": "<receipt_hash>",
      "qa_csv": "<qa_csv>",
      "cloze_csv": "<cloze_csv>"
    },
    "name": "manifesto_commit"
  }
}

Input Schema

Name	Required	Default
`qa_csv`	Yes
`new_ids`	No	[]
`batch_id`	Yes
`deck_dir`	Yes
`new_tags`	No
`cloze_csv`	Yes
`new_topics`	No	[]
`receipt_hash`	Yes
`queue_updates`	No	[]
`catalog_updates`	No	[]
`changelog_entries`	No	[]

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.1Nov 14, 2026

TDQS

A3.6/5.0

Behavior3/5

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

With no annotations, the description must carry the full behavioral burden, and it does disclose meaningful traits: the operation is transactional, requires receipt verification, and is the sole write path. However it is silent on failure/rollback behavior, idempotency of repeated commits, and permission or conflict semantics, which matter for an 11-parameter write 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?

Front-loads the two most important facts (sole writer, transactional) before the prerequisite, and the parameter enumeration is compact. The trailing list is somewhat dense but each item earns its place except for redundancy with the types.

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

Completeness3/5

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

For an 11-parameter mutation tool with no annotations, the definition covers the prerequisite and most parameters, and an output schema exists so return values need not be described. It omits catalog_updates entirely from the parameter list and says nothing about error or rollback outcomes, leaving the agent without guidance for the missing parameter.

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

Parameters3/5

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

Schema description coverage is 0% and the schema types everything as strings, so the description genuinely adds parsing guidance (new_ids is a JSON array of IDEntry dicts, new_tags is comma-separated, queue_updates is a JSON array of strings). But it only gives shape, not meaning — what a queue update targets or how changelog entries are used is left unexplained.

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: "Commits a batch's data transactionally" and positions itself as the "sole writer of the Manifesto," which implicitly differentiates it from read-only siblings like manifesto_state and validate_batch. The domain term "Manifesto" is never explained, so the resource boundary is slightly opaque, but the action is unambiguous.

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

Usage Guidelines4/5

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

Gives an explicit precondition: a valid receipt (content_hash from a validate_batch PASS) is required, which effectively tells the agent to run validate_batch first. It does not state when not to use it or what to do with a failing receipt, but the prerequisite covers the main routing decision.

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

Deploy Server