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

Annotations only cover the safety profile (readOnlyHint=false, destructiveHint=false). The description goes well beyond that, disclosing side effects (ledger account moves, opening balance repriced) and the exact failure protocol: accounts with transactions are refused, unwritten, returning code confirm-required until repeated with confirm true.

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 tight sentences, front-loaded with the operation, then effects, then the failure/retry rule. No filler; each sentence carries information an agent needs.

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?

For a 4-param mutation tool with no output schema, this covers purpose, side effects and refusal behavior well. The remaining gap is what a successful call yields/returns, but that is minor given no output schema exists.

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 coverage is 100%, so the baseline is 3; the schema already documents id, currency, confirm and openingrate. The description adds real meaning on top of that, explaining the confirm gate's error code and the repeat-with-confirm-true workflow, though it says nothing further about openingrate or the base-unit rate semantics beyond the schema.

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 ('Change the currency of an existing bank account by id'), which is a precise sub-operation distinguishable from the broader sibling update_bank_account and from convert_currency. An agent can tell what this does without opening the schema.

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 (existing account, by id) and it describes the refusal/retry path, but it never names an alternative (update_bank_account, convert_currency) or states when this is the right choice versus those. Adequate but without explicit routing.

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