List accounts

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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the description adds real value by disclosing that it reads a local session file rather than calling the bank (implying possible staleness) and that it cannot move money. The data-handling restriction is a genuine operational constraint not encoded anywhere in the structured fields.

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?

Three short sentences, front-loaded with the read-only/consent scope, then behavior, then the disclosure rule. No filler, and the most decision-relevant fact comes first.

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 zero parameters, rich annotations and an output schema, the description covers the remaining gaps: data source (local session file), non-network behavior, and the privacy constraint on displaying results. Only the freshness/refresh semantics of the session file are left implicit.

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 tool takes zero parameters, which is the baseline-4 case; there is nothing for the description to disambiguate. The return-field sentence compensates usefully by describing what the caller gets back.

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-only list of accounts') plus its scope ('covered by the current bank consent'), and enumerates the returned fields. It is clearly distinct from get_balances/get_transactions by resource, though it never names those siblings to route the agent explicitly.

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?

Usage is implied by the consent-scoped framing, and the disclosure instruction ('show the result only to the account owner') tells the agent how to present output. There is no explicit when-to-use/when-not guidance or comparison to the sibling read tools, so the agent must infer selection.

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