Skip to main content
Glama

preview_transaction_automation

Dry-run a set of automation conditions against up to the last 1000 eligible existing transactions and return { matchedCount, scannedCount, matches } where matches is capped at 5 sample transactions. Nothing is modified. Use it to sanity-check conditions before create_transaction_automation or update_transaction_automation. Note that a live automation fires on its own only for newly synced or imported bank transactions that are not transfers and not planned; existing transactions change only when the user runs "Apply to past transactions" for a saved rule in the app.

Input Schema

NameRequiredDescriptionDefault
conditionsYesCondition tree: { match: "all" | "any", items: [...] }. 1-10 items, at most one transactionType item. Item shapes by field: - note | merchant (merchant is the bank-provided merchant/description text): { field, operator, value }. operator: contains_any | not_contains_any | starts_with_any | ends_with_any | equals_any | is_empty. value: 1-20 case-insensitive keywords, max 64 chars each; required unless operator is is_empty. Example: { "field": "merchant", "operator": "contains_any", "value": ["uber", "bolt"] } - payee | account | accountGroup | bankConnection: { field, operator, value }. operator: in | not_in. value: 1-20 UUIDs of that entity, all owned by the user. Example: { "field": "account", "operator": "in", "value": ["<accountId>"] } - amount: { field, operator, value: { min?, max? }, currency }. operator: gte | lte | between | equals. gte and equals take min only, lte takes max only, between takes both. Bounds are decimals (e.g. 12.50). currency: { "mode": "transaction" } compares in the currency of the transaction itself, { "mode": "base" } in the user base currency, { "mode": "specific", "code": "USD" } in a fixed currency. Example: { "field": "amount", "operator": "gte", "value": { "min": 100 }, "currency": { "mode": "base" } } - transactionType: { "field": "transactionType", "operator": "equals", "value": "income" | "expense" } - dayOfMonth: { "field": "dayOfMonth", "operator": "between", "value": { "min": 1, "max": 31 } }

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: 'Nothing is modified' declares the safe read profile, plus a scan bound (last 1000 eligible transactions), a result cap (5 sample matches), and the return shape. It also discloses non-obvious domain behavior about when live automations fire versus existing transactions changing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the operation, then usage guidance, then caveats. Efficient overall, though the final sentence about when a live automation fires is lengthy and somewhat tangential to invoking this specific tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter tool with no output schema, the description fully covers what an agent needs: the dry-run semantics, the scan ceiling, the sampled result shape, and the create/update context. Nothing required to call it correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the nested conditions schema is exhaustively documented (per-field operators, value shapes, examples). The description adds only the phrase 'set of automation conditions' and does not extend parameter meaning beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (dry-run a set of automation conditions) against a specific resource (existing transactions), and explicitly contrasts itself with create/update_transaction_automation. An agent can distinguish it from sibling automation tools without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly says to use it 'to sanity-check conditions before create_transaction_automation or update_transaction_automation,' naming both alternatives and the condition that routes to them. It further clarifies the live-vs-preview semantics so the agent knows when a preview is even meaningful.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.