Create customer

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

Annotations are all false (readOnlyHint, openWorldHint, idempotentHint, destructiveHint), so the description carries the burden of disclosing behavior. It adds valuable detail: the tool validates that a name is present and that at least one of email/phone is given, and it fails on duplicate emails. This goes beyond the schema and gives the agent a clear model of what happens. It doesn't mention the return value or side effects, but for a create operation this is a reasonable disclosure level.

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 three short sentences with no filler. The purpose is front-loaded ('Add a new customer'), followed by essential constraints. Every sentence earns its place, and the structure is easy to scan.

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 tool with four flat parameters, no output schema, and no nested objects, the description covers the key functional requirements and failure modes. It omits the return value (e.g., the created customer object or ID), which could be inferred but isn't stated. Given the simplicity and sibling context, this is a minor gap, making the description nearly 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?

Schema description coverage is only 25% (only notes has a description), so the tool description must compensate. It does so by clarifying the relationship between parameters: 'Requires a name and at least an email or phone' adds a cross-field constraint not present in the schema (which only requires name). It also discloses email uniqueness. This adds meaningful semantic guidance beyond the raw properties, though it doesn't elaborate on phone format or notes usage.

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 begins with a clear, specific verb and resource: 'Add a new customer.' It immediately distinguishes this from sibling tools (search_customers, get_customer, create_booking) by the action and target. The additional constraints (name, email/phone) further clarify its scope without ambiguity.

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 practical usage context by stating the required inputs ('Requires a name and at least an email or phone') and a failure condition (duplicate email). While it doesn't explicitly name alternative tools for non-creation tasks, the sibling names (search_customers, get_customer) make it obvious when this tool is appropriate. This is clear enough for an agent to decide, though it lacks an explicit 'use X instead' note.

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