query_nrql

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

With no annotations, the description carries the full disclosure burden and reveals meaningful behaviors: timeout risk for high-volume apps ('avoid query timeouts'), default result caps ('default is 10 for FACET queries'), and accepted time-range formats. It does not mention output shape or rate limits, but the safety profile of a read-only query tool is largely conveyed.

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 purpose is front-loaded in the first sentence, followed by a dense but purposeful run of NRQL tips; nearly every sentence addresses a common failure mode (timeouts, high-cardinality attributes, unbounded results). It is long, but for a raw query-language tool the guidance earns its place; bullet formatting would improve scannability.

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 tool that accepts arbitrary NRQL with no output schema and no annotations, the description covers event types, time-range formats, query clauses, performance constraints, and defaults — enough scaffolding for an agent to compose a valid query. Minor gaps: it does not describe the response format or how to scope by entity/app name in WHERE clauses.

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% for both parameters, so the schema already names query and account_id. Beyond that baseline, the description adds substantial meaning to the query parameter by teaching NRQL syntax, time-range formats, and best practices (uniqueCount() over uniques(), LIMIT caps, short windows for high-volume apps).

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?

States the exact action — 'Execute a NRQL query against New Relic' — with a clear verb and resource. It is unmistakably distinct from sibling CRUD tools like delete_dashboard or get_incidents, and the enumerated event types (Transaction, Span, Log) further scope what it queries.

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?

Provides rich how-to guidance (SINCE ranges, TIMESERIES, FACET, LIMIT) but no explicit when-to-use or when-not-to-use direction versus siblings such as get_app_performance or entity_search. Selection guidance is only implied: an agent must infer that raw NRQL queries belong here rather than in structured retrieval tools.

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