Export statement CSV

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

Annotations already cover read-only, idempotent, non-destructive and open-world, so the bar is lower. The description still adds real behavioral detail the annotations do not: the CSV is written to disk with owner-only permissions, the path is returned, and inline=true additionally returns the CSV text. It omits what happens on file-name collisions or error conditions, but the side-effect profile is well disclosed.

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 sentences, zero filler, and the core artifact and scope are front-loaded before the optional inline behavior. Every clause earns its place.

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 carries the return contract (saved file path, plus CSV text when inline=true) and the destination directory behavior. It stops short of edge cases such as overwriting an existing file, which is a minor gap rather than a blocking one.

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 description coverage is 100%, so all five parameters including saveAs, accountUid and inline are already documented, giving a baseline of 3. The description restates inline and frames accountUid implicitly as 'the main account', which only loosely matches the schema's env-var/only-account/PRIMARY resolution order, adding little beyond the schema text.

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 (downloads), a specific artifact (Starling's CSV export), the data scope (all settled transactions on the main account) and a range constraint, plus 'the same export as the app' to anchor what the file contains. An agent can separate this from the JSON transaction-reading siblings purely from the text.

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?

Usage is implied: reach for this when a file-formatted statement export is wanted rather than JSON records, and the inline=true cue is a use-time condition. However, with ~50 siblings including list_settled_transactions and list_transactions, the description never names the alternative or states a when-not, leaving the agent to infer the routing.

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