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

The annotations already declare readOnlyHint=false, destructiveHint=false, and idempotentHint=false, so the safety profile is covered. The description goes meaningfully beyond that by disclosing the two-step approval workflow and the fact that no change occurs until execute_approved_action runs, which is exactly the kind of behavioral context annotations cannot express. It stops short of describing return values or failure behavior, but the output schema exists.

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?

Four sentences, but the leading 'Use this when working with RetailHardHat field_operations records in the connected organization' is filler that earns no place, and the trailing sentence about configurable MCP approval requirements is vague hedging. The single most useful sentence (the approval/execute_approved_action gate) is buried in the middle rather than front-loaded.

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?

An output schema exists so return values need no explanation, but this is a mutation tool with a deeply nested, fully undocumented 13-field payload at 0% schema coverage. Beyond the approval gate, the description omits what a well-formed request looks like, which fields are conditionally required (e.g., issueReason when status='issue'), and what happens on validation failure.

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 description mentions no parameters at all. The nested `data` object carries roughly a dozen fields (utilityType, status enum, capacity, meterNumber, serviceAddress, three UUID contact references, dates) that an agent must infer purely from field names and JSON Schema types. With this much nested, undescribed surface area, the description should have explained at least the required fields and the meaning of the enum values.

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 a specific verb and resource ("Create a utility connection"), which cleanly separates it from update_utility_connection, delete_utility_connection, get_utility_connection, and list_utility_connections. The opening sentence about "RetailHardHat field_operations records" is generic boilerplate that adds no specificity, but the core statement is 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?

It describes an important usage condition — nothing happens until a human approves in Settings > MCP and execute_approved_action is called — which tells the agent this is a staged/approval-gated write. However, it gives no guidance on prerequisites (e.g., needing a siteId from list_sites or a utilityCompanyId from list_utility_companies) or when to prefer create_utility_company vs. this tool.

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