get_balance

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

Annotations already declare readOnlyHint and openWorldHint, yet the description adds substantive behavior: consumption order (free → contract → Page Packs), the monthly reset of free pages, the fact that pages_remaining covers only Page Packs, that contract_* keys are omitted absent an API contract, and that statement_pages_remaining is a separate balance OCR does not spend. This is exactly the kind of domain context annotations cannot express.

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?

Front-loads the purpose and the cost-free property in the first line, then unpacks balance mechanics. Dense but every sentence carries unique information about how the number is composed; only the field-name litany is slightly heavy.

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?

An output schema exists, so return values need not be explained, yet the description covers the interpretation pitfalls (partial sum, omitted keys, spent vs unspent statements) that an agent would otherwise get wrong. Nothing needed to call this correctly is missing.

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?

Zero parameters, so the baseline is 4. The description goes further by disambiguating the semantics of individual response fields (pages_remaining vs statement_pages_remaining vs contract_*), which is real added meaning rather than repetition of the empty 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?

States a specific verb and resource ('Get how many pages the FastOCR account can still process') and immediately clarifies cost ('Costs no pages'). No sibling among ocr_file/list_documents/ocr_pdf/get_document/delete_document overlaps with a balance read, so an agent can select it unaided.

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?

Gives an explicit trigger ('Check this before OCRing a large PDF') and points to buy_pages_url for the follow-up action. It doesn't enumerate when-not conditions, but the 'costs no pages' note implies there is no downside to calling it, which covers most of the decision.

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