export_job_splits

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

The description discloses feed-specific behavior beyond the annotation set: pagination via hasMore, continuation token usage, and a non-obvious warning that includeRecentChanges 'may return records sooner but can repeat them'. It also advises polling backoff by telling the caller to 'wait before polling again'. This adds valuable context on top of the readOnlyHint/idempotentHint annotations, with no contradiction.

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 with each earning its place: the first states purpose, the second defines the full pagination and polling sequence, and the third adds a necessary caveat. It is front-loaded, clear, and contains no filler or redundant restatement of schema fields.

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 covers initialization, continuation, polling behavior, and the includeRecentChanges caveat, which is sufficient for a read-only incremental export tool. The output schema can document the exact response fields, so not restating them is acceptable. The main gap is that it never explicitly says to pass the returned continueFrom value as the 'from' parameter on the next request, though it is strongly implied.

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?

Since schema description coverage is 100%, the baseline is 3, but the description adds meaningful usage semantics: 'from' can be a date or omitted to start at the beginning, and 'includeRecentChanges' trades timeliness for possible duplicates. The only ambiguity is that 'continueFrom' is not explicitly mapped back to the 'from' parameter, though context implies it.

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 states a specific verb, 'Read', a specific resource, 'incremental job splits export feed', and an explicit purpose, 'for bulk synchronization'. The name plus description clearly differentiates it from sibling list tools like dispatch_job_splits_list and export_jobs by positioning it as an incremental feed.

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 gives a concrete, sequenced usage protocol: 'Start with a date or omit from', 'continue immediately with continueFrom while hasMore is true', and 'when false retain it and wait before polling again'. It provides clear context on how to paginate and poll, but it does not name alternative tools or specify when not to use this tool, so it stops short of a 5.

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