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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so safety is covered. Description adds meaningful context beyond annotations: server-side durability, returns job id and web url for polling, and the write-scope auth requirement. Doesn't cover rate limits or whether the run can be cancelled after creation.

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 tight sentences: what it does, how it behaves, what it returns, what's required. Front-loaded and no waste.

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?

Covers purpose, durability semantics, return shape (job id + url), and auth scope. No output schema exists, yet the description compensates by naming the return payload. Lacks guidance on when to use autoRun vs pausing, but that's a minor gap.

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%, so baseline is 3. Description mentions files can be attached (mediaKeys) and the model field ('A model test runs the same goal once per model') but adds no more detail than the schema already provides for each parameter.

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?

Clear verb+resource: 'Start a durable job from a goal'. Distinguishes from siblings like jobs_run and jobs_continue by describing server-side durability and the polling return. An agent can tell this creates a new job rather than resuming or listing one.

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?

Implied usage (creating a job when you have a goal), but no explicit when-to-use vs jobs_run, jobs_continue, or jobs_brief. The agent must infer selection from sibling names alone.

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