Skip to main content
Glama

ainote

by io.github.seunghan91

sync_push

DestructiveIdempotent

Push a markdown file into the primary vault. Optional CAS via base_sha to detect concurrent multi-PC writes (Layer 3 of multi-PC sync plan). WAF-bypass tip: large bodies (~10KB+) that get false-positive blocked at Cloudflare can be sent via content_b64 (base64-encoded) OR content prefixed with __B64__: instead. When the push CREATES a new .md file, the response may carry dedup_candidates — existing memory files that look similar (keyword + title similarity, no LLM). It is an advisory, not a rejection: YOU decide to merge into one of them (re-push that path), drop this write as a duplicate (skip), or keep it as a new memory (store).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pathYesRelative file path (e.g., 'global/MEMORY.md', 'launchcrew/firebase.md'). No leading slash, no '..'.
forceNoOptional: when true, skip CAS check even if base_sha is supplied. Use only for intentional overwrites; presence is auditable via warning logs.
contentNoFull file content (markdown text). Alternatively prefix with '__B64__:' followed by base64 payload for WAF bypass.
base_shaNoOptional: git_sha the client last observed for this path. When present, server compares with current git_sha and returns -32009 conflict on mismatch (with current content for 3-way diff). Omit for legacy LWW behavior (response will include a `warning` field nudging clients to upgrade).
device_idNoOptional: client device identifier (e.g., from ~/.claude/ainote-sync/device.id). Stored on FileIndex so future conflict responses can report which device last wrote the path.
content_b64NoOptional: base64-encoded file content (use INSTEAD of `content`). For WAF-bypass on large bodies. Server decodes before storing. If both supplied, content_b64 wins.
supports_supersededNoOptional capability opt-in. When true AND resolves_conflict_id points at an already-resolved conflict whose (path, remote_sha) matches this push, the server returns a NORMAL 200 with resource_data {status:'superseded', reason:'resolved_elsewhere', applied:false, git_sha:<current remote>} instead of a -32009 error, so the client pulls to converge. Omit (default) to keep the legacy -32009 contract.
resolves_conflict_idNoOptional: UUID of a vault_conflicts row this push resolves. When supplied, server validates ownership/unresolved/path/sha and atomically marks the conflict as resolution=clean inside the same transaction as the file_indices write. Validation failure rolls back the whole push and returns -32009 stale_conflict_id.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / $schema
      Added value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed1 schema field changed
    • addedInput schema / properties / supports_superseded
      Added value: +{
+  "description": "Optional capability opt-in. When true AND resolves_conflict_id points at an already-resolved conflict whose (path, remote_sha) matches this push, the server returns a NORMAL 200 with resource_data {status:'superseded', reason:'resolved_elsewhere', applied:false, git_sha:<current remote>} instead of a -32009 error, so the client pulls to converge. Omit (default) to keep the legacy -32009 contract.",
+  "type": "boolean"
+}
  3. First observed

TDQS

A4.3/5.0
Behavior5/5

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

The description goes well beyond the annotations (which already indicate destructive and idempotent behavior). It discloses the conflict detection mechanism (-32009 on base_sha mismatch), the advisory nature of dedup_candidates with explicit decision options, and the WAF-bypass behavior with content_b64. This provides the agent with crucial response behavior and decision framework.

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 description is structured with purpose first, followed by CAS, WAF bypass, and dedup guidance. It is dense but each sentence conveys necessary information. It could be slightly more concise by trimming redundant mentions of content_b64, but it remains efficient for a tool with this complexity.

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?

Given the tool's complexity (8 params, CAS, dedup, WAF) and lack of output schema, the description covers most behavioral aspects: response elements like dedup_candidates and -32009 are mentioned, and the push decisions are explained. However, it does not describe normal success response fields or edge cases like supports_superseded, which are left to the schema. Still, it is largely complete for agent selection and invocation.

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?

The input schema has 100% coverage with detailed descriptions for all 8 parameters, including content_b64, base_sha, force, and resolves_conflict_id. The description reinforces some points (e.g., content_b64 for WAF bypass) but does not add substantial meaning beyond the schema. The baseline of 3 is appropriate since schema does the heavy lifting.

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?

The description clearly states the tool's core function: 'Push a markdown file into the primary vault.' This is a specific verb (push) and resource (markdown file into vault), distinguishing it from siblings like sync_read or sync_delete. It also introduces CAS and dedup features, which further clarifies its role in the sync ecosystem.

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?

The description provides clear context on when to use CAS (concurrent multi-PC writes), when to use WAF-bypass (large bodies ~10KB+), and how to handle dedup_candidates. It implies usage for single-file pushes, distinct from sync_push_batch. While it doesn't explicitly name alternatives or exclusions, the guidance is actionable and context-rich.

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

All ainote toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0
Disambiguation4/5

Most tools clearly target distinct resources (tasks, docs, graph, sync, env_sync, handoffs, judgments, projects, vault). A few pairs could confuse, like sync_push vs vault_sync (which has a push action) and env_sync_write vs env_sync_txn_push, but descriptions mostly clarify boundaries.

Naming Consistency3/5

Names are predominantly snake_case with a noun_verb pattern (e.g., sync_push, task_write), but there are notable inconsistencies: plural/singular mismatches (dev_docs_read vs dev_doc_write, tasks_read vs task_write), verb-first names (list_papers, get_setup_guide, judgment_submit), and a dotted sub-namespace (env_sync.secret_pull) mixed with flat names (env_sync_txn_push).

Tool Count2/5

35 tools is a large surface for a personal note/sync server. While it spans many domains (auth, tasks, docs, sync, env_sync, graph, etc.), the sheer number feels heavy and likely overwhelms agents with too many choices, especially when several tools are consolidated sub-action surfaces.

Completeness3/5

Most domains have reasonable CRUD coverage (tasks, dev docs, graph, sync, env_sync, vault). However, noticeable gaps exist: memory has no write tool (only read), papers only support listing (no create/update/delete), assumptions have write but no dedicated read or delete, and judgment is effectively submit-and-list only.

Resources