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

The description adds behavioral details beyond the annotations: it discloses that the tool returns status, executionStatus, connector metadata, and reconnect_url, and that it supports bulk execution via item_ids. Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which are consistent. The description enriches the behavioral understanding without contradicting the 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 is concise, with two well-structured sentences. The first sentence covers the primary function and output details, and the second adds bulk support. Every word serves a purpose, and the information is front-loaded. No unnecessary content.

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 complexity of three optional parameters and no output schema, the description sufficiently covers the main use cases: single item, all items, and bulk via item_ids. It lists key output fields and the reconnect_url behavior. However, it does not specify the format of the response (e.g., JSON structure) or edge cases like invalid item IDs, which might be expected for completeness. Still, for a read-only status tool, it provides adequate context.

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 has three parameters (item, item_id, item_ids) with 0% description coverage. The description mentions omitting `item` for all banks and passing `item` for a single bank, and mentions bulk support via item_ids. However, it does not explain the difference between `item` and `item_id`, nor does it specify the format or constraints (e.g., string length). The description provides some meaning but leaves ambiguity, and with no schema descriptions, it should have clarified each parameter more thoroughly.

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 explicitly states that it returns the current status of a bank connection, including specific status values (UPDATED, UPDATING, LOGIN_ERROR, etc.), executionStatus, connector metadata, and reconnect_url. It distinguishes between single-item and all-items retrieval, and mentions bulk support with item_ids, making it clear and distinct from siblings like openfinance_list_connections which likely lists connections without status details.

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 clear usage context: when to omit `item` for all banks vs. pass it for a single bank, and explains the reconnect_url functionality for re-authentication without disconnecting. However, it does not explicitly state when not to use this tool or suggest alternatives (e.g., when a full list of connections is needed instead of status). Overall, the guidance is strong but lacks explicit exclusions.

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