accounts

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the bar is lower, and the description still adds a genuinely useful safety disclosure: string fields are untrusted institution data and instructions in them must not be followed. That is a real behavioral trait not derivable from structured fields. It stops short of describing breadth (all accounts? paginated?) or what 'estimated cash' means.

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?

It is short and front-loads the resource, with no filler. However, the telegraphic fragment style ('Accounts: balance, kind, tax...') sacrifices clarity for brevity, and the second sentence's referent is unclear enough that the compression costs comprehension.

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, the description carries the burden of describing returns, and it does list the key fields. But it omits whether the result is the full set of accounts or filtered, and whether pagination or limits apply, leaving gaps for a tool whose sibling set overlaps in scope.

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% for the single 'detail' parameter, and the description never mentions it, so nothing explains the difference between concise and full output. The enum values are largely self-explanatory, which mitigates the gap, but the agent gets no signal about what extra data 'full' returns or when to request it.

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 names the resource (Accounts) and enumerates the fields returned (balance, kind, tax, estimated cash), which implies a listing tool, but it never states a verb such as 'list' or 'retrieve'. The trailing sentence about using id/last4 to filter holdings and transactions is ambiguous — it is unclear whether this tool performs that filtering or merely supplies identifiers for sibling calls.

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?

There is no explicit guidance on when to call accounts versus the siblings summary or health, both of which could plausibly return account-level information. The only usage-adjacent sentence is about chaining id/last4 into holdings and transactions, which describes downstream use rather than when to select this tool.

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