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

Annotations only declare readOnly=false, destructive=false, openWorld=false; the description goes well beyond them by disclosing that the tool is never executed directly, returns status='confirmation_required' with an action_id and plan_token, and requires confirm_action to complete the write. That is exactly the non-obvious behavioral context an agent needs for a mutating tool, and it is stated unambiguously.

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 parameter summary come first, followed by a clearly labeled CONFIRMATION block, so the most decision-relevant fact is easy to find. The prose is dense and nearly waste-free, though the all-caps emphasis and run-on parameter sentence make it slightly less scannable than it could be.

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?

For a write tool with no output schema, the definition covers purpose, all five parameters, and the propose/confirm lifecycle, which is the critical unknown. It stops short of stating what the confirmed result contains, how duplicates are handled, or what happens if the plan_token expires.

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?

With 0% schema description coverage, the description carries the full burden and does enumerate every parameter, marking 'name' as required and explaining that organization_id links to an organization. What is missing is any format or validation hint for email and phone beyond the maxLength already in the schema.

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 first sentence gives a specific verb and resource ("Create a contact (person) in the ERP") plus scope ("under the caller's company") and attribution ("caller's employee record"). It is clear what the tool does, but it never distinguishes itself from the sibling create_contact_personal, so the ERP-vs-personal boundary is left implicit.

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?

Usage is implied by the scope statements (under the caller's company, attributed to the caller's employee record), which lets an agent infer this is the company-level contact creation path. There is no explicit when-not guidance and no named alternative such as create_contact_personal, so the agent must infer the routing decision.

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