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

With no annotations, the description carries the full disclosure burden, and it does disclose the primary side effect: an email with a PDF link is sent to a recipient. However, the recipient logic is ambiguous — 'to the invoice email, or to "to"' does not clarify whether the `to` parameter supplements or replaces the invoice email, and there is no mention of failure behavior when the invoice has no email on file. The core action is transparent, but edge-case behavior is left to inference.

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 entire description is one dense sentence that front-loads the action and resource before the formatting hint and recipient clauses. There is no filler — every phrase either names the action, establishes the input contract, or clarifies the destination. The only minor blemish is the triple-use of 'to', which is compact rather than verbose.

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 simple 2-parameter, 1-required-parameter tool with no output schema, the description plus schema covers the essential call calibration: valid number format is exemplified, the recipient parameter is explained, and the source of valid numbers is identified. Remaining gaps — what happens if the invoice lacks an email address, and whether both recipients receive the message — are real but minor for such a small surface.

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, but the description adds genuinely useful value: it reveals the exact number syntax (RX- prefix for invoices, PF- for proformas) that the raw schema descriptions ('Invoice number from list_invoices') do not provide. This example-based format guidance materially reduces the chance of an invalid call.

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 verb 'Email' with the resource 'existing invoice or proforma' states precisely what the tool does, and the concrete number examples (RX-2026-000123, PF-2026-000007) pin down the accepted input. The word 'existing' implicitly contrasts with sibling issue_proforma, and the reference to list_invoices distinguishes the sourcing flow. The recipient clause 'or to "to"' is slightly awkward but decipherable and does not obscure the core action.

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 instruction to use an 'exact number from list_invoices' gives the agent a clear sequencing guideline: look up the number first, then call this tool. 'Existing' also implies the precondition that the invoice/proforma must already be issued rather than created. However, it does not explicitly name an alternative (e.g., issue_proforma for creation) or state when not to use this tool, so it stops short of full exclusion guidance.

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