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

Annotations only say readOnlyHint=false and destructiveHint=false. The description adds substantive behavior beyond that: the call is staged, nothing is applied until a human approves the exact request in Settings > MCP and execute_approved_action runs, and business workflow approvals always apply on top of admin-configurable settings. It does not mention duplicate handling despite idempotentHint=false, which is the remaining gap.

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 approval gating sentence is the highest-value content but is buried third. "Create vendor." merely restates the tool name and "Use this when working with RetailHardHat vendors records in the connected organization" is generic filler that costs space without adding selection signal.

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, and the approval workflow is well covered. The description is still thin for a nested 13-field payload with zero schema coverage — it should at least indicate required vs optional fields and the status enum semantics.

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 single "data" parameter is a nested object with 13 properties including a status enum, so the schema does not explain field meaning. The description only says "Required fields are validated by the application," which tells the agent nothing about which fields exist, which are required, or what values like status accept.

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 states a specific verb+resource ("Create vendor") in the RetailHardHat vendor domain, so an agent can tell it apart from get_vendor, list_vendors, update_vendor and delete_vendor. It does not explicitly name those siblings as alternatives, which keeps it from a 5.

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 gives a precondition context ("no change occurs until a human approves... execute_approved_action is called") and mentions org-configurable approval, which is real usage guidance. However, it never says when to create a new vendor versus updating an existing one or creating a contact, and gives no exclusions or prerequisites for the data itself.

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