Start a job

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

No annotations are provided, so the description must fully disclose behavior. It states it returns a session but does not reveal whether the operation is destructive, requires specific permissions, or any rate limits. For an action that modifies state, this is a significant gap.

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?

Two sentences, front-loaded with the core action, and zero wasted words. Highly efficient and easy to parse.

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?

Given the tool's simplicity (one param, no output schema, no annotations), the description covers purpose, return value, and follow-up steps. It lacks prerequisites (e.g., job must exist and be enabled), but these are reasonable assumptions. Overall, sufficiently complete.

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% with one well-described parameter. The description adds minimal extra context (mentioning list_jobs), but the schema already provides the necessary 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?

The description clearly states the action ('Start a backup/replication job now') and specifies the resource (a job). It distinguishes from siblings like stop_job and retry_job by focusing on starting. The purpose 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?

The description implies the workflow by mentioning subsequent tools (get_session/get_session_logs), providing context for use. However, it does not explicitly state when not to use or list alternatives, but given there is only one start tool, the guidance is sufficient.

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