lemma_create_card

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well. It flags that this is a mutation ('WRITE'), creates a real financial instrument, and carries a severe consequence if used carelessly. The explicit approval requirement and the spending-limit warning go well beyond a generic 'create' description, though it stops short of covering failure modes or irreversibility.

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?

The description is three sentences with no filler. The action and risk are front-loaded, and the parenthetical about the entire account balance earning its place by preventing a catastrophic mis-call. Every sentence adds critical 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?

For a high-stakes mutation with five parameters, no output schema, and no annotations, the description covers the essential decision and invocation needs: what it does, the mandatory approval, and the unmissable spending-limit requirement. The only notable gap is not explicitly telling the agent to source bank_account_id from lemma_list_bank_accounts, but the overall safety-critical guidance makes this a minor omission.

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 60%, so the schema already documents confirm, reference, and spending_limits. The description adds valuable context for spending_limits by explaining why at least one is required, but it does not compensate for the undocumented bank_account_id and nickname parameters. An agent would still need to infer what those refer to, though 'drawing on a Lemma bank account' hints at bank_account_id.

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 opens with a stark 'WRITE -- CREATES A REAL FINANCIAL INSTRUMENT' and then names the exact action: 'issue a virtual debit card drawing on a Lemma bank account.' It uses a specific verb and resource, and the contrast with sibling tools like lemma_get_card, lemma_delete_card, and the move-money tools is immediately clear.

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 gives clear operational prerequisites: at least one spending limit is REQUIRED, and explicit user approval is required before every call. It explains why the limit is mandatory by warning that a card without limits could spend the entire account balance. It does not explicitly name alternatives, but the context makes it evident this tool is for the creation step, not retrieval or deletion.

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