get_balanceReturn total, reserved, and available MainBook credits. Every value is measured in PDF pages.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
| Name | Required | Description | Default |
|---|---|---|---|
| units | No | pages | |
| balance | Yes | ||
| reserved | Yes | ||
| available | Yes | ||
| explanation | Yes |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description states that values are in PDF pages, which goes beyond the readOnlyHint annotation (which already marks it as safe/read-only). The openWorldHint annotation is present but the description adds the specific unit detail. There is no contradiction with annotations.
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 description is extremely concise: two short sentences that capture the tool's purpose and the unit of measurement. Every word adds value, and it is perfectly front-loaded with the core function.
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?
Given the tool has zero parameters, an output schema exists to define return values, and there are no complex behavioral traits, the description is fully adequate. It is complete for the intended use case.
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?
There are zero parameters, and schema coverage is 100%, so there is no burden for the description to explain parameter meaning. The description does not add any additional parameter semantics, which is fine—baseline 3 is appropriate.
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 uses specific verbs ('Return') and clearly identifies the resource ('total, reserved, and available MainBook credits') and the unit ('measured in PDF pages'). It is distinct from sibling tools like 'convert_bank_statement' or 'get_conversion' which deal with conversion operations, not balance retrieval.
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?
Although there is no explicit 'when to use' versus 'alternatives' statement, the context signals show zero parameters and the sibling tools are all about conversion—not balance. The description implicitly makes clear that this is a straightforward query tool with no filtering needed, and no trade-offs exist among siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct, non-overlapping purpose: convert initiates a full workflow, get_balance queries credits, get_conversion retrieves a specific job's state, and list_conversions enumerates jobs. No ambiguity between them.
All tool names follow a consistent verb_noun snake_case pattern: convert_bank_statement, get_balance, get_conversion, list_conversions. The convention is uniform and predictable.
Four tools is well-scoped for a bank statement converter: one primary conversion action plus three supporting query/status operations. No bloat or missing core functionality.
The set covers the full conversion lifecycle (create, upload, start, poll, retrieve) along with credit checking and job listing. A minor gap is the lack of an explicit cancel/delete operation, but this is not a critical workflow dead-end.