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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact — results are partial ("found so far") — but says nothing about whether completion is signalled, whether polling is expected, or what happens to results after completion.

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?

One short sentence with zero filler, and the key qualifier ("started with start_batch") is placed where it is read first. Nothing could be removed without losing meaning.

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?

For a polling tool with no output schema, the description should characterize the return shape — progress fields, row format, how completion or failure is indicated. It only hints at this with "progress and the rows found so far," leaving the agent to discover the response structure by calling it.

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 100% and the single id parameter is already documented as "The batch id from start_batch." The description reinforces that provenance but adds no format, validation, or edge-case detail beyond the schema.

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 names the resource (a batch) and what is returned (progress and rows found so far), which is enough to tell it apart from start_batch and the lookup/balance siblings. It is a noun phrase rather than an explicit verb, but the retrieval intent is unambiguous.

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?

It states the prerequisite clearly — the batch must have been created by start_batch, and the id comes from there. It does not say when to call it versus alternatives, how often to poll, or what to do once the batch finishes, so usage is only implied.

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