Start a job

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

Annotations establish this is a non-read-only, open-world, non-destructive write. The description goes beyond them by disclosing that the run is durable and continues server-side, that it returns a job id plus a web url for polling or continuation, and that the write scope is required. That is meaningful operational context an agent cannot get from the hints alone; lacking are only details like rate limits or whether concurrent runs are permitted.

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 short sentences, front-loaded with the action and its durability, then the return shape, then the auth requirement. Every sentence carries information the structured fields do not, with 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 a nine-parameter, async, open-world write tool, the description covers what it does, that execution outlives the call, what comes back, and the required scope. An output schema exists so return values need no further expansion. The only gap is guidance on how this job differs from the other job-lifecycle siblings.

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 explains goal, files, label, model, autoRun, budgetUsd and the rest in detail. The description only echoes the optional file attachment, adding nothing about the higher-value parameters such as model, autoRun, or budgetUsd. 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 ('Start a durable job from a goal') with the optional file attachment noted. It is unambiguous what the tool does, but it never distinguishes itself from adjacent siblings like jobs_continue or jobs_run, which an agent must infer from the name alone.

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 supplies a precondition ('Needs the write scope'), which is real guidance, and the phrase 'start ... from a goal' implies creating a new run. But there is no explicit when-to-use versus jobs_continue/jobs_run/jobs_run, and no when-not-to-use condition, so routing among the job family is left to inference.

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