runrunit_create_task_branch

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

With no annotations, the description carries the full burden and does well: it discloses the safe dry-run default, that no checkout occurs, that it does not commit, and that it hands off to runrunit_commit_per_file when includes_commit is true. It omits auth/permission needs, idempotency, and behavior when the branch already exists, so not a 5.

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?

Four short sentences, front-loaded with the core action and default, then the approval gate and handoff. No filler; every sentence conveys operational information.

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 no annotations and no output schema, the description covers the critical plan/apply gate, absence of commit, and tool chaining. It leaves gaps around failure modes (existing branch, missing repo) and the shape of the returned plan, but is otherwise sufficient to call correctly.

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 documents every parameter, establishing a baseline of 3. The description restates the approved/include_commit semantics that the schema already provides (e.g. next_tool is runrunit_commit_per_file), adding little beyond it.

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 states a specific verb+resource ('plans or creates only the branch task_[número]') and names the related sibling runrunit_commit_per_file, so an agent can place it in the workflow. It is clear what the tool acts on, though 'only the branch' scope is implicit rather than contrasted against other creation siblings like runrunit_create_task.

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?

It gives a clear default ('Default is plan (no checkout)') and an explicit condition for the mutating path ('Pass approved:true after the user accepts the plan'). It does not enumerate when-not scenarios or name alternative tools beyond the downstream commit tool.

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