export_receipts

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

With no annotations, the description carries the full burden, and it does disclose two real behavioural traits: the result is text rather than a written file ('write it wherever it belongs') and rows are ordered oldest first. It does not state whether the export is complete or paginated when since/until are omitted, nor any permission or rate constraints.

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?

Two short sentences, front-loaded with the resource and scope, and the second sentence carries the non-obvious return-behaviour detail. The trailing 'for expense records' is mildly redundant but does add framing, so no significant waste.

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 correctly takes on the return-value burden by stating the export is returned as text and is ordered oldest first. It leaves open what 'every spend' means when both bounds are omitted, but otherwise the agent has what it needs for a zero-required-parameter read export.

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 67%; the since/until ISO 8601 bounds are described in the schema itself. The description compensates for the undocumented format parameter by stating the output is 'CSV or JSONL text', clarifying both the allowed values and that the result is a text payload.

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 (export) and resource (receipts) plus the content that is exported: every spend in the ledger. This is clear enough to call the tool, but it does not explicitly distinguish itself from near neighbours like list_payments or get_usage, leaving the agent to infer the difference from the word 'export'.

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?

The phrase 'for expense records' implies the intended use case, so usage is inferable, but there is no explicit when-to-use, when-not-to-use, or named alternative among the many payment/usage/ledger siblings. An agent must guess whether this or list_payments is the right source.

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