nrql_batch_query

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It does disclose the core behavior — multiple queries executed in one request for efficiency. But it omits meaningful edge behaviors such as maximum query count per request, partial-failure semantics (does one bad query fail the whole batch?), and how errors are surfaced. These matter for a batch tool and are undocumented.

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?

A single front-loaded sentence that states purpose and benefit with zero waste. Every clause earns its place; it is appropriately sized for the tool's simple surface area.

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 presence of an output schema and a well-documented parameter schema reduces the burden substantially. However, the one-sentence description leaves genuine gaps for a batch operation: query-count limits, failure isolation between queries, and result-keying behavior are absent, and with no annotations these gaps have nowhere else to be filled.

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 `queries` parameter is already well-documented with an example dict mapping labels to NRQL strings. The description adds no parameter-level detail beyond what the schema provides, so the baseline of 3 applies.

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+resource ('Run multiple NRQL queries in a single request') and explicitly frames the batch nature, which distinguishes it from the nrql_query sibling. The phrase 'more efficient than individual calls' makes the differentiation concrete without needing to open either 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?

'More efficient than individual calls' gives clear context that this tool is for aggregating multiple queries in one round-trip. However, it does not explicitly name nrql_query as the single-query alternative nor state when NOT to use the batch tool (e.g., for one-off queries or when query-count limits matter), leaving exclusions implicit.

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