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

Annotations supply destructiveHint=true so the write nature is already flagged, and the description adds the concrete endpoint (POST /jobs) and the cents convention. It does not disclose any post-creation side effects, permission requirements, or validation behavior such as invoice_number uniqueness unless supplied.

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?

A single dense sentence with the mandatory preconditions and the dependency lookup front-loaded, followed by the endpoint. No filler.

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 an 11-parameter nested mutation with no output schema, the description covers the essentials an agent needs before calling: required ids, where to get the address id, and units. It omits what comes back (presumably a job id) and how to proceed afterwards, which limits it slightly.

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 only 55%, but the description only loosely summarizes the optional surface ('optionally scheduled, assigned, tagged and with line items') and repeats the cents convention already documented on unit_cost/unit_price. It does not clarify ambiguous fields like lead_source, business_unit_id, or anytime_start_date.

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 a job') plus hard scope constraints: the customer and address must already exist. That implicitly separates it from housecall_create_customer, housecall_create_estimate and housecall_create_lead, though no sibling is named explicitly.

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 a clear precondition (existing customer, existing address) and routes the agent to housecall_get_customer for address ids, which is genuine when/how-to-use guidance. It stops short of stating when NOT to use it (e.g. estimates vs jobs, dispatch) or what the alternatives are.

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