conduyt_reply_capture_setup

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

With no annotations present, the description carries the full burden and does most of it: it discloses an external side effect (creating a domain at the provider), a hard precondition, the full set of 409 meanings including the irreversible case ('retired names are permanently unavailable'), and a redirect to suggestedDomain-based retry. It stops short of saying whether a completed or half-finished setup can be undone, even though conduyt_reply_capture_remove exists among siblings.

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?

Front-loaded with the action and return value, then constraints, then next step. The long 409 disjunction is the one heavy sentence, but each clause corresponds to a distinct failure mode the agent must distinguish, so little of it is waste.

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?

One optional parameter, no output schema, and no annotations: the description compensates by explaining the returned DNS records, the prerequisite, the legal naming space, the follow-up verification step, and every documented failure branch. An agent can drive the whole setup-and-verify flow from this text alone.

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 coverage is 100% and the single property is already documented, so a baseline of 3 would be defensible. The description earns more by supplying the concrete default shape ('reply.<sending-domain>'), the strict-subdomain validity rule, and the retired-name caveat with the 'reply2.<domain>' workaround, all of which are semantics the schema does not express.

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 verb and resource ('Start reply-capture setup: creates the receiving domain at the email provider and returns the DNS records to add'), which tells the agent both the mutation and the return payload. It is clearly distinct from the sibling verify and get tools it names.

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?

Explicit about when it applies ('Requires a verified sending domain first'), what input is legal (strict subdomain of the account's verified sending domain, anything else refused), and what to do next ('After adding the DNS records, call conduyt_reply_capture_verify'). It also names the recovery path when 409 blocks the call.

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