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

Annotations declare readOnlyHint=false and destructiveHint=false, and the description adds real context beyond them: no customer notification, internal-only record, autopilot (no confirmation), and that the response includes the starting milestone. It does not mention permissions scope beyond API key access.

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 with purpose then side-effect/runtime behavior; nearly every sentence earns its place. The closing API-key/access sentence is somewhat boilerplate but relevant to setup.

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 annotations covering safety and no output schema, the description covers what is created, where it appears, that no customer contact occurs, and the return shape (job with starting milestone). Sufficient for correct invocation.

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 all four parameters (including the priority enum and the address default) are already documented. The description largely restates the address default rather than adding new parameter meaning, so 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 ('New job for a contact, at the job site address') and clarifies it 'opens a job for an existing contact', which distinguishes it from read siblings like acculynx_get_job or acculynx_list_jobs. It doesn't explicitly name an alternative, but the create-vs-read distinction is unambiguous.

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?

Clearly sets the precondition ('for an existing contact') and the side-effect context that selects it ('adds a record your team sees and sends nothing to the customer, so it runs without asking'). No explicit when-not or named alternative (e.g., create_contact first), but the triggering context is well conveyed.

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