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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds significant behavioral context beyond annotations: the reconnect_url behavior (reopens widget in UPDATE mode, no disconnection, no slot consumption), the difference in response shape between omitting and passing `item`, and the bulk execution behavior. This is exactly the type of context an agent needs.

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 well-structured: a first sentence states core functionality, followed by usage variations and bulk support. Every sentence adds value—no fluff or redundancy. It is information-dense but still easy to parse.

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?

This is a read-only, idempotent tool without an output schema, so the description must handle return-value explanation. It does mention key fields (status, executionStatus, connector metadata, reconnect_url) and the list response shape (`{ count, items }`), but it does not specify the exact response shape for a single item or clarify the `item_id` parameter. Slightly incomplete but mostly sufficient.

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?

With 0% schema description coverage, the description must compensate. It explains `item` (single vs. all) and `item_ids` (bulk), but does not explain `item_id` at all, nor its relationship to `item`. This leaves one of three parameters ambiguous, so compensation is only partial.

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 states a specific verb ('Returns') with a specific resource ('bank connection') and enumerates the fields returned (status, executionStatus, connector metadata, reconnect_url). It distinguishes itself from sibling list tools by mentioning the reconnect functionality and bulk support, making the purpose 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 gives clear context for single vs. all banks ('Omit `item`... pass `item`') and mentions bulk support with `item_ids`. It does not explicitly name alternative tools or state when not to use it, but the usage scenarios are implied strongly enough to guide an agent.

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