Scan a task in progress (reconcile vs the diff)

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

Beyond annotations (readOnlyHint, destructiveHint, idempotentHint), the description adds key behavioral traits: 'Never a verdict' and the non-error result for absent worktree. These clarify the tool's safe, read-only, and consistent behavior without contradicting annotations.

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 sentences with no fluff. The first sentence front-loads the core purpose and output. The second provides sibling context. The third edge case. Every sentence is essential.

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?

Given the tool's complexity (2 params, simple), the description covers purpose, output (structured result), edge cases, and relationship to sibling. Output schema exists, so no need to detail return format.

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% and parameters are fully described. The description does not add new semantic details beyond what the schema provides, such as the format of 'task' or 'base'. Baseline 3 is 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?

Clearly states the tool reconciles a task against its spec and worktree diff to surface coverage gaps, out-of-scope changes, and self-report mismatches. Differentiates from sibling swarm_reconcile_review by noting 'Same engine as reconcile_review' and adding context 'before a review packet exists' and 'Never a verdict'.

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?

Explicitly says when to use ('before a review packet exists') and what the tool does not do ('Never a verdict'). Mentions an edge case behavior ('returns a structured not runnable here result, not an error'). Does not explicitly list alternatives, but the sibling reference provides differentiation.

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