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

Goes well beyond the annotations (readOnly=false, destructive=false, openWorld=true) by disclosing the side-effect that an invoice is also created ('returns the job and the invoice that goes with it'), the consent requirement ('confirm with the user before each call'), and the auth dependency ('Needs the user's Cotlet API key'). These are genuine behavioral traits an agent needs before calling.

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-loads the purpose, but wastes space with near-duplicate sentences ('Create a job for a customer with line items...' / 'Creates a job for a customer and an address with service line items') and repeats the confirmation rule twice ('By default you confirm each call...' / 'confirm with the user before each call'). Also mentions 'tags,' which is not a parameter.

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 mutation tool with no output schema, it covers side-effects, the returned resources, scheduling constraints, consent, and auth. The main gap is that required vs optional parameters (customer_id, line_items) are left entirely to the schema rather than reinforced in prose.

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 description coverage is 100%, so the schema already documents each parameter including the rule that team_member_ids is required when scheduled_start is set. The description restates the schedule/dispatch rule but adds no format or syntax detail beyond the schema, 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+resource ('Create a job for a customer') and scopes it precisely with line items, optional schedule, and dispatched team member, clearly distinguishing it from siblings like create_customer, create_estimate, and list_jobs. An agent can select it 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?

Provides real conditional guidance: 'Leave schedule out to save it unscheduled' and 'When you schedule it, you must also dispatch at least one team member.' It also frames the confirmation/consent flow. It stops short of naming alternative sibling tools (e.g., quoting via create_estimate first), so not a 5.

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