sync_start

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

With no annotations, the description fully discloses key behaviors: asynchronous execution (returns { jobId } without waiting), polling via sync_status, job retention (only one job kept), and loss on server exit. It also explains impact on unchanged and missing files. This goes well beyond basic safety hints.

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?

Three sentences, no fluff, all information is relevant and front-loaded. It efficiently covers purpose, async behavior, job lifecycle, and parameter scoping in a compact form.

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?

The description is complete for a tool of this complexity: it explains the return value, polling mechanism, job limitation, and optional path semantics. No output schema exists, so return-value explanation is sufficient. It covers all critical operational aspects.

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 schema already provides 100% coverage for the single 'path' parameter, including optionality, base directory behavior, and scoping rules. The description adds no new parameter semantics beyond what the schema says. Baseline 3 is appropriate.

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?

The description clearly states the tool's purpose: 'Reconcile the index with the files on disk' with specific actions (ingest new/changed, leave unchanged, remove gone). This distinguishes it from siblings like ingest_file (single file ingest) and delete_file, and it explicitly notes the async jobId return and polling via sync_status.

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?

The description implies when to use it: to reconcile the index with disk, with optional path scoping. It provides context on behavior (leaves unchanged files alone) but does not explicitly state when not to use it or name alternatives (e.g., use ingest_file for a single file). Still, context is clear and useful.

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