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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, and the description adds substantial context beyond them: the deterministic contract rules validated (version marker, record shape, required fields, addresses, severity, thresholds), the exact return shape (result, issue_count, issues with code/severity/message and provenance, summary by code), and an explicit disclaimer of runtime/safety certification.

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?

Purpose and argument routing are front-loaded and every sentence contributes (validation scope, return shape, limits, disclaimer). It is dense as a single block of prose rather than being broken into scannable segments, which slightly hurts readability but not substance.

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?

With no output schema and 0% schema description coverage, the description compensates fully by enumerating return fields and their meaning, plus the boundary of the tool's responsibility — an agent has everything needed to call it correctly and interpret results.

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 description coverage is 0% and the parameter titles are unhelpful, so the description must carry the burden — and it does, defining each of the three arguments as the complete CSV text for a specific export type (FactoryTalk View tags, digital alarms, analog alarms) and clarifying all are optional.

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 opens with a specific verb and resource: 'Check a supplied CSV before importing it into an HMI project.' It scopes the check to HMI import CSVs and clearly differs from the sibling hmi_preflight_service_info, which by name is a service-metadata tool rather than a CSV validator.

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 explicitly states when to use it ('static import preflight only'), when not to ('does not connect to any HMI or PLC and does not certify runtime or safety behavior'), and how to select each argument by export type, including that arguments may be omitted when that type is not being checked.

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