Skip to main content
Glama
meshive-mcp

meshive-mcp

Official
by meshive

Set Watched Folders

set_watched_folders
Idempotent

Update a running pod's watched folders without restarting it. Read the current set first, then submit the complete configuration with the expected version to avoid conflicts.

Instructions

Replace a running pod's watched folders without restarting it. Read watched_folders first and send the WHOLE set back: template = {template folder path: {"enabled": bool, "include": [...] or null}} and user = [{"path", "include", "enabled", "include_existing"}]. expected_version is the revision you read; a version conflict means someone else changed it — read again. A running pod's template folder can't be moved: to save another folder instead, turn the template folder off and add the new path to user (the app keeps writing to $MESHIVE_OUTPUT_DIR, so tell the user to point the app there). Adding or turning on a folder can raise storage costs (uploaded files are stored and billed): with confirm=false (default) such a change only returns a summary; call again with confirm=true and the returned pod_name after the user agreed. Removing or turning off applies immediately. Every write requires operation_id. Reuse the ID returned by the preview, or generate a UUID before the first call. Keep it for confirmation and all retries; a new ID means a new operation. After a timeout, check operation_status and resource state before retrying.

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": {
      "pod": "<pod>",
      "expected_version": "<expected_version>"
    },
    "name": "set_watched_folders"
  }
}

Input Schema

NameRequiredDescriptionDefault
podYes
userNo
confirmNo
templateNo
workspaceNo
operation_idNo
expected_versionYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only give safety hints (readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=true); the description goes well beyond them by disclosing the two-phase preview/confirm gate, the billing consequence of uploads, the immediate-apply behavior for removals, and version-conflict semantics. It also explains the operation_id lifecycle including timeout recovery via `operation_status`, which is not derivable from any structured field.

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 replacement premise and the read-first prerequisite are front-loaded, and each subsequent block (version conflict, template constraint, cost/confirm, operation_id) is a distinct concern with no filler. It is dense and long, with nested parentheticals that slow scanning, but no sentence is redundant.

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 7-parameter, open-world mutation with an output schema present, the description covers everything the agent needs to act safely: correct sequencing, cost-gated confirmation, conflict recovery, and idempotent retry strategy. Return values are left to the output schema as expected, with only the identifiers the agent must echo back (`pod_name`, `revision`) mentioned.

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 description coverage is 0%, so the description must carry the load, and it does for the hard parameters: it gives the literal shape of `template` ({path: {"enabled", "include"}}) and `user` (list of path/include/enabled/include_existing), plus the meaning of `expected_version` and `operation_id`. It leaves `pod`, `workspace`, and `confirm`'s interaction only partially explained (confirm is covered operationally rather than semantically), so it stops short of full coverage.

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 first sentence names a specific verb and resource ("Replace a running pod's watched folders") plus a defining constraint ("without restarting it"). That immediately separates it from the read-only `watched_folders` sibling, which the description explicitly tells the agent to read first.

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?

It states the prerequisite (read `watched_folders` and send the whole set back), the version-conflict recovery path ("read again"), and the alternative when a running pod's template folder can't be moved (turn template off, add path to `user`). The confirm=false preview vs confirm=true commit flow is spelled out with the exact ordering, and removal/turn-off is called out as immediate.

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