Create Contact

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

With no annotations provided, the description carries the full burden of behavioral disclosure and does so excellently. It warns that distinct_id must be a real external identifier, instructs the agent to ask the user if missing, and explicitly states 'Do NOT invent one or copy it from any other field.' It also discloses the 'never overwrites' behavior, required field conditions, return value, and potential ValueError, covering safety and error semantics thoroughly.

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?

Despite the length, the description is well-structured with Args, Returns, and Raises sections and front-loads the most critical facts (purpose, overwrite behavior, required field constraint, and the ask-if-missing rule). Each sentence adds value, such as parameter constraints and warnings, with no redundancy or fluff.

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?

The description is exceptionally complete for a no-annotation, no-output-schema tool, covering usage, parameters, return value, and errors. The only notable gap is that it does not specify what happens if a contact with the same distinct_id already exists—whether it creates a duplicate or fails. This missing behavior is relevant given the tool's emphasis on creating new contacts.

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?

The input schema provides zero descriptions (0% coverage), so the description must fully compensate—and it does. For every parameter, it adds meaning beyond type/name: distinct_id gets length limit and provenance rules, email gets RFC822 format, email_consent gets enum values, and properties gets item structure and a concrete example. This transforms ambiguous schema fields into actionable guidance.

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 clearly states the tool's purpose: 'Create a new contact in Tidio.' It distinguishes itself from siblings by emphasizing 'Always creates a new contact; existing data is never overwritten,' which differentiates it from update_contact and delete_contact. The verb 'create' and resource 'contact' are specific and 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?

The description provides strong context for usage, specifying that a new contact is always created and never overwrites existing data, which implies it is for new contacts only. It also gives a clear constraint ('At least one of email, first_name, last_name, or phone must be provided') and the requirement for distinct_id. However, it does not explicitly name alternatives like update_contact for existing contacts, relying on sibling names and implication instead.

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