elba_unpaid

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

With no annotations, the description carries the full burden and does substantial work: it discloses the reconciliation behavior (paid/cancelled re-read only on divergence), the effect of recheck_all, and a failure mode — debt comes back null if any amount is unknown or an invoice failed to re-read. Missing are cost/latency implications of recheck_all and any permission requirements.

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?

Four tight sentences: what is returned, the reconciliation rule, the flag, then the output shape and null condition. Front-loading the resource and putting output details last is the right order. Density is high but nothing is padding.

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 and no annotations, the description steps in to enumerate the returned fields (number, client, project, amount, paid, days outstanding, link) and the null-debt edge case, which is exactly the burden it must carry. Remaining gaps are ordering, whether the result is paginated or bounded, and how 'unpaid' is scoped by date.

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 0% — recheck_all has a bare boolean with a default and no explanation — so the description must compensate, and it does: it defines the flag's effect as re-reading all invoices rather than only divergent ones. For a single parameter that is adequate, though it doesn't say how expensive the all-invoices path is.

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 states a specific resource and filter: unpaid invoices assembled from the journal status plus the payment feed, with the paid portion reconciled. That is far more than a restatement of the name. It does not explicitly contrast itself with siblings like elba_report or elba_payment_news, so an agent still has to infer which aggregation it wants.

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 rather than stated: the agent learns that paid/cancelled invoices are re-read only when the feed diverges from the journal, and that recheck_all=true forces a full re-read. That is genuinely useful selection logic for the single parameter, but there is no explicit when-to-use/when-not guidance and no sibling is named as an alternative.

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