netsuite_execute_suiteql

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

With no annotations, the description carries the full burden. It explicitly declares read-only behavior, restricts to SELECT queries, and reveals important behavioral traits: default limit=100, max limit=1000, offset default=0, and the auto-conversion of 'LIMIT N' to 'FETCH FIRST N ROWS ONLY'. The warning about syntax is valuable and beyond the schema. This is thorough for a query tool.

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 description is well-structured: purpose statement, parameter summary, important warning, and three practical examples. It is front-loaded with the most critical information and every sentence adds value. The warning and examples are directly useful for correct invocation, and the length is appropriate given the complexity of SQL queries.

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 the lack of output schema and annotations, the description provides enough context for an AI agent to select and use the tool: safety constraints, parameter defaults, syntax caveat, and realistic examples. It does not describe the return format, but for a generic query tool the output depends on the query, so this is acceptable. The tool's complexity is moderate and covered well.

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 only 33% (only query has description). The description compensates by specifying the query as a SQL SELECT statement and adding defaults and maximum for limit (100/1000) and default for offset (0). It does not fully explain pagination semantics (e.g., that limit caps result size), but the examples illustrate usage. This is good compensation for the schema's gaps.

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 clearly states the tool's function: 'Execute a read-only SuiteQL query against NetSuite.' It uses a specific verb (execute) and resource (SuiteQL query), and adds crucial constraint 'Only SELECT queries are allowed.' This distinguishes it from sibling tools that target specific record types (e.g., netsuite_get_vendor_by_id).

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 clear context for when to use this tool: when you need to run a read-only SQL query against NetSuite. It provides multiple examples illustrating common use cases. However, it does not explicitly state when not to use it or name alternatives, such as using specific getter tools for well-known records. The guidance is clear but not exhaustive.

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