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

Annotations already flag this as a non-destructive, open-world write. The description adds real value beyond them: nothing is sent to the customer, the invoice remains editable afterwards, it returns the total, no confirmation prompt is needed, and it requires a Cotlet API key with app access. It stops short of describing idempotency or what happens with zero charges.

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 correctly, but the 'nothing is sent' point is made twice ('Nothing is sent' and 'It sends nothing to the customer'), and the opening sentence largely restates the second one. Roughly half the text is redundant.

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 one-parameter write tool with no output schema, the description covers side effects, reversibility, auth needs, and the return value (the total). Only edge cases such as behavior when the job has no charges are unaddressed.

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?

With a single parameter at 100% schema coverage, the schema already documents job_number and even points at list_jobs/list_opportunities/get_job. The description adds no syntax or sourcing detail beyond 'a job', so the baseline 3 applies.

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 ('Create the invoice for a job from its charges') and scopes it precisely: derived from job charges, not a blank invoice. It also implicitly separates itself from the sibling kickserv_send_invoice by stressing nothing is sent.

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 context for use (mirrors 'Generate Invoice' in the job header, operates on an existing job's charges) and a strong when-not signal by ruling out sending. It never names an alternative tool or states prerequisites like 'job must already have charges' explicitly.

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