Count Records

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

Without annotations, the description carries the full burden. It mentions using Stats API for efficiency, but does not disclose limitations such as error handling on invalid queries, potential rate limits, or that the output is a single integer count. The description is adequate but lacks depth on behavioral behaviors beyond the core function.

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 two short paragraphs: the first succinctly states the function and method (Stats API, efficient), the second provides usage examples. Every sentence adds value, and there is no repetition or unnecessary text. It is optimally concise.

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 absence of annotations and output schema, the description effectively covers the tool's purpose, usage context, and parameter semantics. It could be slightly more complete by explicitly stating that the return value is a single integer count, but this is implicitly clear. For a simple counting tool, the description is sufficiently complete.

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?

All three parameters are described in the input schema (100% coverage), and the description adds value by explaining the 'query' parameter with encoded query string examples (e.g., 'active=true^priority=1'), the 'instance' parameter's fallback to env variable, and clarifying the 'table' parameter with ServiceNow-specific examples. This goes well beyond the schema definitions.

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 verb 'count' and the resource 'records on any ServiceNow table', and distinguishes from siblings like query_table by emphasizing efficient server-side counting via Stats API. The purpose is specific and 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?

The description provides concrete examples of when to use the tool ('gauge data volumes' with open P1 incidents, users in a group, etc.) and implies it is for quick counts rather than retrieving records. However, it does not explicitly state when not to use it (e.g., when full record data is needed) or name alternative tools like query_table for fetching records.

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