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

Annotations already flag destructive/openWorld/idempotent, but the description adds what they can't: admin-only authorization, asynchronous acceptance semantics ('202/queued means accepted, not completed'), the retry rule for idempotency keys, and the explicit scope exclusion that these orders bypass the ConnectReseller customer wallet and local domain portfolio.

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 authorization constraint and capability dependency are front-loaded, and each following sentence adds a distinct operational fact (account vs domain routing, key reuse, async polling, intent requirement, scope). No sentence restates another or repeats structured data.

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 destructive, open-world, asynchronous transaction tool with a 0%-covered schema, the description supplies everything else needed: prerequisites, parameter sourcing, retry policy, and how to confirm completion. An output schema exists, yet the description still adds the 202-vs-completed distinction that matters for agent control flow.

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 0% and the nested input object is untyped, so the description carries the full burden and does so: it names the source of action/input values, explains when domain_id vs account_id apply, and defines idempotency_key's stability requirement on retries. This compensates well for the schema's silence.

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 ('submit a middleware transaction') and immediately scopes it to middleware admin operators, which separates it from the many read-side middleware_* siblings. It also names the sibling it depends on (middleware_get_capabilities) and the sibling it hands off to (middleware_get_transaction).

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 routing rules: action/input come from middleware_get_capabilities, domain actions need domain_id, account actions use the selected enabled account, and account_id is only needed when several accounts are enabled. It also tells the agent to poll middleware_get_transaction after a 202/queued and to require explicit user intent for paid or destructive actions.

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