create_contact

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

With no annotations, the description carries the behavioral burden and does add real value: it discloses that the same email address on different domains produces separate records with independent consent, preventing the common assumption of email-based global uniqueness. It does not cover duplicate-within-domain behavior or response details, but the key non-obvious side effect is surfaced.

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?

Two sentences with no filler. The first sentence front-loads the action, resource, and endpoint; the second adds the one genuinely non-obvious nuance needed to use the tool correctly.

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 core domain-first identity semantics are well covered, but operational gaps remain: no mention of what happens on a duplicate within the same domain, no return/response information (and no output schema exists), and no explicit routing to batch import tools for large lists. These are meaningful gaps for an agent handling edge cases.

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 descriptions already cover email, domain, properties, and unsubscribed (67%), and the description adds meaning beyond that by explaining the identity model: an address is only unique within a domain and consent is domain-scoped. This clarifies the relationship between domain, email, and unsubscribed beyond the literal schema text.

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 action ('create'), a clear resource ('contact in a sending domain's contact pool'), and the HTTP endpoint. The domain-first scoping distinguishes it from related tools like create_contact_property and update_contact.

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?

Gives clear context: this is the single-contact creation path for a domain-scoped contact pool, and the domain-first note tells the agent where the resource belongs. It does not explicitly call out bulk alternatives like import_contacts_batch or import_contacts_csv, but the single-vs-bulk distinction is strongly implied by the wording and sibling names.

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