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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds genuinely useful context: no delivery side effect occurs until send_invoice runs, the invoice_id is returned, and a scoped Cotlet API key is required. This is real disclosure beyond the annotations.

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 and short overall, but the 'nothing is sent yet / nothing is sent to the client until send_invoice runs' point is made twice, and the opening 'Invoice for a job with its items and total' duplicates the sentence that follows. Trimming the redundant restatement would sharpen it.

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 2-param creation tool with no output schema, the description covers what it does, the delivery boundary, the returned invoice_id, and the auth requirement. Nothing critical to correct invocation 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 job_id and due_date are fully documented in the schema. The description adds only that items and total are inherited from the job (not passed in), which is mildly useful but does not explain due_date semantics. Baseline 3 is appropriate.

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 ('Creates an invoice from a job, with the job's items and total'), and it is immediately distinguishable from sibling send_invoice and list_invoices. An agent knows exactly what entity is produced without opening the schema.

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?

Explicitly routes the agent: 'Nothing is sent to the client until send_invoice runs', which contrasts this creation step with the sibling that actually delivers. Adds a behavioral directive ('this call runs without asking'). Lacks broader when-not guidance (e.g., duplicate invoices), so not quite a 5.

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