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

With no annotations, the description carries the full burden and does disclose the key non-obvious behavior: this is asynchronous, the customer approves out-of-band in the MB WAY app, and the outcome must be fetched via mbway_check_status. It omits retry/idempotency behavior around order_id, request expiry, and what happens if the customer declines, so it is strong but not complete.

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?

Three short sentences, front-loaded with the action and the required customer step, ending on the actionable next call. No filler or restatement of the name.

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 payment-initiation tool with no annotations and no output schema, the description covers the essential flow and the mandatory polling step. It is nearly complete, missing only failure/timeout and decline handling, which an agent would reasonably need for error paths.

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 description coverage is 100%, so all five parameters (including the country-code#number phone format and the max-15-character order_id) are already fully documented in the schema. The description adds no additional parameter meaning, so the baseline 3 applies.

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 ('Sends an MB WAY payment request') and pins the distinctive mechanism ('customer's mobile phone' with approval 'in the MB WAY app'), which separates it from the card/PIX/Payshop payment siblings. It also names the paired tool mbway_check_status, so the agent can place it in the flow without opening a 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?

'Use mbway_check_status to check the result' gives explicit follow-up guidance and implies the async two-step pattern. It does not, however, say when to choose MB WAY over the other create_payment siblings or what preconditions (valid MB WAY key, reachable phone) must hold, so it stops short of full when/when-not coverage.

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