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

Goes well beyond annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true) by disclosing that nothing is sent or charged, that confirmation is required by default, that it reaches other people, and that an API key is needed. Rich behavioral context.

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 description is eight sentences for a one-parameter tool and repeats the not-sent idea twice and the confirmation idea twice. Front-loaded purpose is good, but several sentences could be merged.

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?

Covers prerequisites, side effects, authentication, and confirmation policy, but with no output schema it omits what the call returns (e.g., invoice ID), which an agent might need to chain to send_invoice. A small gap keeps it from a 5.

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% (job_id documented as 'Job ID from list_jobs'), so the single parameter is fully specified in the schema. The description mentions the job context but adds no parameter detail, matching the baseline 3.

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 the specific action—creating an invoice from a job's products/services/charges—and explicitly distinguishes it from send_invoice, so an agent can tell it apart from the sibling that delivers the invoice.

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?

Provides a clear condition for use (job must normally be Completed/closed, with the preference exception) and names the alternative send_invoice for sending. The 'Nothing is sent or charged' line clarifies when-not to use it.

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