Create Transaction Rule

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety class is known. The description adds genuinely new behavioral facts: rules without a criterion are silently ignored on later edits, apply_to_existing_transactions rewrites past transactions immediately and is hard to undo, and the tool does not affect rule priority. These are consequences beyond the annotation flags.

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 purpose and the hard prerequisite are front-loaded, and the criteria/actions sections are cleanly grouped with headings and inline examples. It is dense but nearly every line carries operational meaning; only slight tightening would be possible.

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?

For an 11-parameter, non-idempotent, destructive creation tool with an output schema present, the description covers the prerequisite criteria rule, every parameter's meaning, ID sources, and the irreversible side effect. Return values need not be described since an output schema exists, so nothing material 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?

Schema description coverage is 0% at the top level, so the description carries the full burden and does so thoroughly: it documents each criterion shape with concrete examples, defines operator semantics, explains is_expense sign behavior, maps account_ids/category_ids to their matching role, and enumerates every action parameter including the 'name, not an ID' distinction for set_merchant_name. This compensates completely for the undocumented 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?

The opening sentence gives a specific verb and resource (create an automation rule), which plainly separates it from update_transaction_rule and delete_transaction_rule siblings. It does not, however, name or contrast any sibling explicitly, which caps it below a 5.

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 real usage conditions: a rule needs at least one of merchant/statement/amount criteria or later edits are ignored, and it warns to validate criteria with search_transactions before using apply_to_existing_transactions. It also routes the agent to get_transaction_categories for category IDs. It stops short of saying when to prefer update_transaction_rule instead, so no explicit alternative routing.

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