Export Transactions

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

Descriptors are already covered by annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) and the description's 'Read-only' is consistent with them. The description adds genuinely valuable behavioral context beyond annotations: the leading-apostrophe CSV escaping to prevent spreadsheet formula injection, and a warning that large date ranges produce large output. Not exhaustive (no header-row or ordering guarantees), but substantial.

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 long but every sentence carries distinct payload: purpose, column semantics, formula-injection defense, usage routing, and output-size caveat. It is front-loaded with the core purpose. The only redundancy is 'Read-only', which merely repeats the annotations — minor, given the density of genuinely useful information.

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 100%-covered schema, rich annotations, and an output schema, the description fills the important remaining gaps: the CSV format itself, dollar/negative-as-outflow column semantics, and the security-critical escaping behavior. Minor omissions such as header-row presence and exact date formatting are acceptable because the output schema exists and the core calling decision is fully supported.

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 8 parameters including the type enum and the one-year default in sinceDate are already documented structurally. The description only adds the cross-tool context 'same filters as get_transactions, including type', which helps an agent re-use knowledge of the sibling tool but does not enrich individual parameter meaning. Baseline 3 applies.

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, resource, and output format: 'Export transactions as CSV text' with the exact column list spelled out (date, amount, payee, category, etc.). It is clearly differentiated from its most similar sibling, get_transactions, by the 'same filters as get_transactions' note plus the JSON-vs-CSV contrast.

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?

Provides an explicit routing rule: 'Use when the user wants data for a spreadsheet or offline analysis; for programmatic work prefer get_transactions (structured JSON).' It also gives operational guidance to narrow with filters when date ranges are large, leaving no ambiguity about when this tool is the right choice.

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