sync_status

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

With no annotations, the description carries the full burden and delivers real behavioral detail: only the latest job is retained, stale or pre-restart jobIds error out, and the distinction between non-failing conditions (relabelled, unreadable, 'labels:' prefix) and genuine failures is spelled out. It omits auth/permission requirements and any polling-cost or rate-limit guidance, so it is strong but not exhaustive.

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?

The first two sentences are properly front-loaded (action, return shape, error constraint), but the remaining three paragraphs are dense prose about count semantics that an output schema already carries. It is informative rather than wasteful, yet roughly four times longer than a one-parameter poll tool needs.

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?

Given an output schema exists, the description need not restate return fields — yet it supplies the interpretive layer the schema cannot: what relabelled and unreadable mean, when a folder error escalates to job failure, and what invalidates a jobId. Nothing an agent needs to poll correctly and interpret the result 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?

Schema coverage is 0% for the single jobId parameter, so the description must compensate — and it does, implying the id comes from sync_start and constraining it to the currently retained job (an old or pre-restart jobId raises an error). It stops short of stating the id format or explicitly saying it is the value returned by sync_start.

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 and resource ("Poll a sync job started by sync_start") and explicitly ties the tool to the sibling that produces the job. An agent can distinguish it from sync_start (which creates jobs) and status (a different, unscoped status tool) without opening the schema.

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 first sentence routes usage to jobs created by sync_start, and "Only the latest job is retained — an old jobId, or any jobId from before a server restart, raises an error" tells the agent exactly which jobIds are valid. It does not contrast against the sibling 'status' tool or advise on polling cadence, so it stops short of full when/when-not guidance.

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