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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower, yet the description adds real value: it scopes the output to status and timestamps only, explicitly excluding account numbers, balances and transactions, and explains that reconnect.eligible carries a plain-language reason. It stops short of describing pagination, latency, or what an empty connection list looks like.

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?

Front-loaded with the purpose and scope in the first clause, then the field inventory, then the exclusions, then the follow-up loop. Dense but almost entirely load-bearing; the closing sentence about itemId is slightly convoluted in phrasing though it does carry unique information.

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?

With no output schema and no parameters, the description bears full responsibility for explaining the return shape, and it does: it lists the states, the timestamp, and the nested reconnect eligibility with its reason. An agent knows both what it will get back and how to act on it.

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?

Zero parameters, so the baseline is 4. The description still adds meaning to the returned itemId, clarifying that it names one connection and is the key referenced when a fresh sign-in is proposed, which helps an agent chain this read into a reconnect flow.

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?

States a specific verb and resource ('Read the health of YOUR OWN bank connections') and enumerates exactly what is surfaced: itemId, bank name, working/sign-in/stopped/removed/paused state, last update time, and reconnect eligibility. No sibling tool covers bank connections, and the 'YOUR OWN' scope plus the itemId framing makes the boundary 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?

Clear context for when to call: to check connection health and to see whether a reconnect can be prepared, plus an explicit re-read after the person reconnects to confirm. It does not name exclusions or alternative tools, but no sibling offers overlapping functionality, so the guidance is sufficient without a routing clause.

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