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

Goes well beyond the annotations (readOnly=false, openWorld=true, destructive=false) by disclosing the state transition (Draft invoice becomes Awaiting Payment), the outbound nature of the action, the default confirmation-on-each-call behavior and how to disable it, regional channel constraints, and the API key requirement.

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 core action is front-loaded, but the second sentence ('Sends the invoice by email or text message') restates the first, and the 'Jobber:' prefix duplicates the title. The genuinely new information (state change, region gating, confirmation behavior) follows the redundancy, slightly burying the value.

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 send action with no output schema and full parameter documentation, the description covers everything an agent needs: what it does, the state effect, who is contacted, the confirmation requirement, and the auth prerequisite. Nothing material is missing.

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 real meaning for the channel parameter: email links to the invoice in client hub and text delivery is limited to the US, Canada, and the UK. That regional constraint directly informs channel selection. It says nothing extra about invoice_id beyond what the schema covers.

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 ('Send an invoice to the client') plus the delivery mechanism and the resend case. An agent can immediately distinguish this from siblings like jobber_create_invoice, jobber_get_invoice, or jobber_record_payment.

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?

Gives clear operating context: 'or send it again' covers the resend case, and it explicitly warns 'Reaches other people: confirm with the user before each call.' It does not name alternative siblings or state when this should NOT be used, which keeps it short of a 5.

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