jules_get_diff

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

No annotations are provided, so the description carries the full burden. It usefully discloses the timing constraint (only meaningful after execution/milestone steps begin), but says nothing about error behavior if the diff is not yet available, permission requirements, or whether the diff can be large/paginated.

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 sentence with no filler, front-loading the resource fetched and appending the timing condition. Every clause earns its place.

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 one-parameter read tool with no output schema, the description states the resource and the precondition, and it implicitly tells the agent what is returned (diff plus PR link). The missing piece is failure-mode behavior when the diff does not yet exist.

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?

Only one parameter exists and schema description coverage is 100%, so the schema already documents taskId fully. The description adds no format, source, or constraint details beyond it, making the baseline 3 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?

States a specific verb (fetches) and a specific resource (git diff and PR link) that no sibling provides, so an agent can distinguish it from jules_get_task_status or jules_list_tasks. It stops short of explicitly naming a sibling to contrast against, so it lands at 4 rather than 5.

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 phrase 'once execution or milestone steps have started' gives an implied precondition for when the tool is useful, which is real guidance. However, it never says what to do if called too early, nor does it point to alternatives such as jules_get_task_status for checking readiness.

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