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

No annotations are provided, so the description carries the full behavioral burden. It implies a safe read scoped to 'this API key', but discloses nothing about auth failure behavior, rate limits, whether a missing or default api_key resolves to a server-side key, or what happens at zero balance.

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?

One tight sentence with no filler; the value returned is front-loaded. The only criticism is the interrogative phrasing, which reads more like a question about the tool than an instruction for using it.

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 trivial single-value read the description does convey what the returned number means, which is the essential piece. However, with no annotations, no output schema, and an undocumented parameter, gaps remain around the api_key argument and error/edge behavior.

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?

The single api_key parameter has 0% schema description coverage, and the description never explains that it exists, that it is optional (default ''), or how an empty value is resolved. With one undocumented parameter the description should compensate but does not.

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 states precisely what the tool returns: the number of scanned pages remaining on the current API key before a top-up. That is specific enough to separate it from siblings like get_result and parse_invoice, though it is phrased as a question and never names an explicit verb or resource (e.g. 'balance'/'quota').

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?

There is no statement of when to call this versus alternatives, no prerequisites, and no mention of the relation to the sibling topup_link (which presumably addresses the low-balance case). The agent must infer the trigger condition entirely.

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