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

Goes well beyond the annotations: discloses the required PUSHNOTIF_API_KEY, that the order is PENDING and expires in 30 minutes at zero fee, that crediting happens automatically on webhook confirmation (i.e. the call does not itself deliver credits), and the amount_rp-vs-package_id precedence. This is the mutation lifecycle detail an agent needs and cannot get from readOnlyHint/destructiveHint alone.

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?

Dense but front-loaded: purpose first, then exclusion, then auth/lifecycle, then parameter conflict, then return shape. Every clause carries information, though the inline JSON return shape makes the sentence long and slightly heavy to parse.

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?

With no output schema, the description usefully spells out the returned JSON fields including qris_checkout_url and expires_at. The remaining hole is behavior with zero arguments, since both parameters are optional and the description never says which one is defaulted to.

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% so the baseline is 3, and the description adds the flat Rp 0.20/credit rate, the Rp 1,000 minimum, and the precedence rule in prose. It does not state what happens when neither optional parameter is supplied (required params = 0), which is the one semantic gap.

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 ('Create a prepaid credit top-up invoice') plus the payment rail (Indonesian QRIS, all banks and e-wallets), which makes it trivially distinguishable from billing/status siblings. An agent knows exactly what is being created 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?

Explicitly names the trigger ('when the user wants to purchase additional credits') and the anti-trigger with the exact alternative tool ('do not use it to check whether an existing invoice has been paid (use check_billing_and_qris_status instead)'). No inference required.

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