list_transactions

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

With no provided annotations, the description carries the full burden of behavioral disclosure. It discloses important behavioral constraints: date format (YYYY-MM-DD), acceptance of names or ids, partial string matching for notes, and return fields with currency (USD). It does not mention pagination or potential high-volume results, but for a list operation the core behaviors are well covered. The description compensates well for the lack of annotations.

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 consists of four focused sentences, each contributing unique value: the primary action with filters, date format, flexible identifier handling, return fields, and references to helper tools. There is no redundant or filler content, and the main purpose is front-loaded. It is concise while remaining informative.

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 that all 6 parameters are optional and an output schema is present, the description provides a complete mental model: how to filter, what data comes back, and where to get filter values. The return fields are listed explicitly, and the sibling tools offer additional context. For a read-only list tool, the description adequately covers both usage and expectations without needing to detail every edge case.

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?

The input schema already describes all parameters (100% coverage), establishing a baseline of 3. The description adds meaningful semantics beyond the schema by explaining that account, category, and payee accept either names or ids (the schema only explicitly mentions this for payee), and that notes is a partial search. It also cross-references the list_* tools, tying parameter usage to a practical workflow. This extra context justifies a 4.

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 description clearly identifies the action ('List transactions') and the resource ('from Actual Budget'), with optional filters. It distinguishes from sibling tools like list_accounts and add_transaction by specifying the returned entity type (transactions) and the context (Actual Budget). The scope is unambiguous.

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 description provides practical guidance by directing users to list_accounts, list_categories, and list_payees to obtain valid names for filters. This implies when to use the tool (when you need transaction data with filtering) and how to prepopulate filters. It doesn't explicitly contrast with mutation tools (add/update/delete), but the 'list' verb makes the read-only intent clear. Overall, strong context but missing an explicit 'use this when' statement.

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