Refresh linked accounts

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

The description explicitly says the call waits for completion by default and then returns fresh account metadata, which is behavioral context beyond the readOnly/idempotent/destructive annotations. It discloses that the operation triggers an external request to linked institutions, implying a possible delay, and that omitting account_ids broadens the scope to all accounts. It does not describe poll/timeout interplay, but the presence of those parameters in the schema covers them.

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?

Two short sentences with no filler; the central behavior and the key default-scope rule are front-loaded. Every clause contributes information, making the description efficient and 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?

The definition captures the triggering behavior, the default blocking behavior, and the all-account refresh case, which covers the main decisions for a 4-parameter tool with no required parameters. It leaves out any explanation of the polling parameters and does not mention what kind of errors may surface, but the output schema and numeric constraints cover much of the remaining 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?

With zero schema description coverage, the description must carry parameter meaning; it explains account_ids via the omission rule ('Omit account_ids to refresh every account') and wait via 'wait for completion by default.' It gives no semantics for poll_seconds or timeout_seconds, so an agent must rely on their names and numeric constraints alone. This partial coverage justifies a middle score.

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 uses a specific verb ('Ask linked institutions') and identifies the resource (linked accounts), clearly distinguishing this from retrieval tools like get_accounts. It also states the default wait behavior and the all-account scope in the second sentence, leaving no ambiguity about what function the tool performs.

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 no guidance on when to choose this over alternatives such as get_refresh_status or get_accounts; it never mentions when a refresh is appropriate or when to instead read cached data. The only usage hint given is account scoping ('Omit account_ids to refresh every account'), which is parameter guidance rather than tool-selection guidance.

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