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

This is a mutation tool (destructiveHint=true, openWorldHint=true) and the description adds substantial context beyond the annotations: order is non-binding until the seller accepts, no payment flows through the platform, replies are asynchronous, and confirm is required for owner-gated steps. It stops short of warning that a sent interaction cannot be retracted or that idempotency comes from client_request_id, which the annotations alone don't convey.

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 type list is front-loaded immediately after the framing sentence and each clause carries distinct information with no filler. The paragraph is dense and semicolon-chained, which slightly slows scanning for a nine-parameter tool, but nothing is redundant.

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 complex, nine-parameter nested tool with no output schema, the description covers the async result path, the owner-confirmation step, and the binding semantics of orders and agreements. What an agent actually receives on success (an interaction id, a status field) is left implicit, which is the main remaining gap.

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 56%, and the description compensates well for the type parameter: each of the six enum values is explained with its payload concept (free text plus proposed terms, template plus params, quantity-based price, up to 3 slots, post-agreement contact exchange). It adds little about dry_run or client_request_id beyond what the schema already says, so not a 5.

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 names a specific verb ('Start an interaction') plus the four target resource prefixes (off_, pty_, ned_, mch_) and enumerates all six interaction types with a short semantic gloss for each. An agent can distinguish this from siblings like respond or request_attestation without opening the schema.

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?

It states explicit routing rules: 'message' is always allowed while every other type requires it to appear in the target's `accepts`; the async answer path routes to get_inbox, and status=awaiting_owner routes to confirm after asking your human. Alternatives and their triggering conditions are named rather than implied.

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