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

Goes meaningfully beyond the annotations by disclosing the two-phase nature: the call only creates a bill, 'nothing is charged by this call', and money moves only when the owner pays in Kaspi — resolving the obvious misreading of readOnlyHint=false. It does not address non-idempotency (repeated calls presumably create multiple bills) or any auth/ownership requirements, which is why it stops short of 5.

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 compact sentences, front-loaded with the action and amount range, then the mode semantics, then the card alternative. No filler or repetition of structured fields beyond the useful amount bound.

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 does describe what each mode produces (a bill pushed to the app, or a QR to pay). It stops short of saying what identifiers/status the response carries, so an agent cannot confirm what to report back after the call.

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 50%, and the description compensates for the undocumented parts: it defines what method=push and method=qr do, ties phone to the push flow, and restates the $1-1000 amount bound. Only amount_usd and method specifics like the phone format are left to the schema.

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?

Specific verb+resource: 'Put a Kaspi bill for a balance top-up of $1-1000', with the two delivery modes spelled out. This is clearly distinguishable from dosai_get_balance (reading) and dosai_get_cabinet_link (the card path), which 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?

It explicitly routes the alternative case: 'For a card, give the cabinet link: dosai_get_cabinet_link with place=top_up', and explains which method value applies when (push = bill into Kaspi app of a phone, qr = QR to pay from Kaspi.kz). The agent knows both when this tool applies and where to go otherwise.

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