sync_start

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

With no annotations, the description carries the full burden and does: async job semantics, differential ingest rules, move-in-place chunk retention, job retention limits ('only the latest sync job is retained... a server restart discards the previous job's record'), and the exclusive-lock failure mode. This is exactly the behavior an agent needs before firing a long-running job.

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

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

Front-loaded with the action and the immediate return (jobId), then progressively adds detail that each earn their place — the diff semantics, the retention caveat, and the locking rule. No filler sentences.

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

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

An output schema exists, so return shape needn't be spelled out, yet the description still tells the agent what to do with the jobId. Combined with the concurrency and retention caveats, nothing needed to invoke this correctly is missing.

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

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

The single optional parameter has 0% schema coverage and no description in the schema, but the description supplies its meaning: it scopes the reconciliation to 'one path inside' the document roots versus the default full-root sweep. It stops short of stating path format (relative vs absolute), so not a 5.

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

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

Opens with a specific verb+resource: 'Reconcile the index with the document roots'. The parenthetical scope '(or one path inside them)' pins down the boundary, and the described effects (ingest new/changed, skip byte-identical, remove vanished) clearly separate it from ingest_file and ingest_data.

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

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

Gives an explicit follow-up ('poll sync_status until state is succeeded or failed'), an explicit failure condition (another sync in progress, including an external `minirag-mcp sync`), and an explicit non-overlap guarantee ('single-file ingests and queries are never blocked'), which routes the agent to ingest_file for one-off work.

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