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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description reinforces with concrete consequences: the job "appears on the team's schedule" and "cannot be deleted through this API; creating twice makes two jobs." It does not cover permissions/auth needs or the response payload, keeping it below a 5.

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?

Three sentences, front-loaded with the read/write marker and the core action, ending with the endpoint. The field enumeration is long but aids scanning of a 40-parameter schema; little is wasted, though some of the list duplicates schema keys.

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 destructive, non-idempotent 40-parameter creation tool with no output schema, the description covers the key risks (no delete, duplicate creation) and lookup prerequisites, but never says what is returned (e.g., the new job ID) or how partial payload failures behave. That leaves a meaningful gap for an agent planning a follow-up get_job call.

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 35% across 40 parameters, so the description must compensate and does so only partly: it enumerates the optional groups (address, category, source, techs, tasks, notes, products, services, other charges) and points to lookup tools for name-based fields. Roughly two-thirds of parameters — dates, duration, payment fields, custom_fields, gate/follow-up flags — get no mention in the description.

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?

Opens with a specific verb and resource ("create a job (work order) for a customer") plus a scoping note on optional groups, which cleanly separates it from siblings like servicefusion_create_customer and servicefusion_create_estimate. The parenthetical clarifying "work order" also resolves terminology ambiguity.

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 an explicit prerequisite ("Look up category, source and status names with the list tools first"), naming the sibling list tools conceptually. It states no exclusion criteria against create_estimate, but the domain context (job vs. estimate) is reasonably implied by the resource name.

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