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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=true, so the safety profile is largely covered. The description reinforces this with 'sensitive write operation' and the confirm requirement, but adds little beyond the structured fields and the endpoint path; no side effects on the invoice itself are described.

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?

Two short, front-loaded sentences: the action/endpoint first, then the limitations. Every clause carries information and nothing is padded.

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 9-parameter destructive tool with no output schema and only 67% schema coverage, the description is thin: it does not explain the optional email/message targeting, workspace scoping via account_id, or authentication, which an agent would need to call it correctly.

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 67% and the only parameter the description mentions (confirm=true) is already fully documented in the schema, so it adds no new meaning. It says nothing about email, message, account_id, or the auth parameters, leaving the semantic gaps in the schema unaddressed.

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 ('Sends') plus resource ('an invoice') and even names the exact endpoint POST /:account_id/invoices/:invoice_id/send, which cleanly distinguishes it from create_invoice, update_invoice, mark_invoice_paid and export_invoice in the sibling list.

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 a prerequisite ('requires confirm=true') but offers no when-to-use/when-not guidance relative to the many sibling invoice tools (e.g. mark_invoice_paid, export_invoice, update_invoice). Usage is implied by the verb rather than explicitly scoped.

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