client_statement_email

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

Annotations only say non-readonly, non-destructive, non-idempotent, open-world. The description adds substantive behavior beyond that: the bulk send halts at the plan's daily/burst e-mail limit and reports `stoppedReason`, and dry run reveals skipped recipients (no e-mail, below minimum balance, unsubscribed). That is exactly the context annotations can't convey.

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?

Front-loaded with the action and subject, then the single-vs-bulk branching, then the dry-run recommendation, then prerequisites and limits — no filler sentence. It is dense and long-ish, but every sentence contributes operational 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?

No output schema exists, yet the description explains what dry run returns (recipients plus skip reasons) and that bulk sends surface `stoppedReason`. Combined with the permission and plan prerequisites, an agent has everything needed to call this safely without surprises.

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 already 100%, so baseline is 3; the description earns extra by explaining cross-parameter relationships the schema states only individually — `to` must be an address of one of your clients, `minBalance` applies only in bulk mode, and `dryRun` returns the statement itself for a single client. It doesn't cover `asOf` or `companyId` semantics, but those are adequately in 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 ("E-mail the statement of unpaid invoices ... with the PDF attached") plus the literal subject line, which distinguishes it from generic siblings like invoices_email or client_statement. An agent can tell exactly what artifact leaves the system.

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?

Explicitly branches usage: pass `uuid` for one client (with `to` constrained to one of your client addresses), omit it for a bulk send gated by `minBalance`, and recommends `dryRun: true` first to preview recipients and skip reasons. It also states prerequisites (invoice-sending permission, plan with e-mail sending), which is stronger than most sibling tools.

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