integrate

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

No annotations are supplied, so the description must carry the behavioral load. It does disclose the important traits: apply results in uncommitted changes, the operation is all-or-nothing, symbol_scope jobs are merged by symbol for Python files, discard deletes the worktree and branch (destructive), and conflicts can spawn a reconcile job.

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?

The text is dense with semicolons but every clause carries information, with no filler and no repetition. The run-on format hurts parseability a little, but it is still front-loaded and compact.

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?

This is a mutating tool with a destructive discard path and no annotations or output schema. The description covers action semantics and conflict behavior but says nothing about what is returned, what happens to already-applied changes, or how ids is interpreted, which is a substantial gap for this operation.

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 0%, and the description explains action (apply, discard) and auto_resolve meaningfully. It never says what ids refers to (job IDs? worktree IDs?) and never lists the full set of valid action values, even though the schema has no enum. That leaves a real gap.

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 verb phrase 'Bring worktree jobs back' plus the apply/discard/conflict breakdown identifies the operation as integrating completed worktree job results into the main workspace, which is more specific than the generic name 'integrate'. It does not explicitly contrast itself with other lifecycle tools such as cleanup or stop, so it is clear but not fully differentiated.

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?

'diff first to review' tells the agent to inspect before integrating, and the apply vs. discard vs. auto_resolve clauses set out the conditions that select each path. What is missing is guidance on prerequisites, for example whether the job must have finished before integrate is valid.

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