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

Beyond simple annotations, the description explains the complex operational behavior, such as the full gated merge chain it uses, its state retention while pending, and the internal mechanisms used (like `last_attempt.reason`). This is valuable behavioral context.

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?

Despite its technical density, the description is highly concise, using structured prose to layer complex logic efficiently. Every sentence provides unique operational insight.

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?

The definition is extremely complete for this complex feature. It covers not only the immediate action but also the upstream triggers, downstream persistence, and necessary context (like write access and scope) required for correct use.

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?

While schema coverage is high, the description adds critical semantics, specifically clarifying that `enabled` is true for arm and false for disarm, and that `merge_method` is restricted to 'merge' only.

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 purpose is explicitly defined as arming or disarming auto-merge on a specific PR, clearly identifying the resource (PR) and the state being controlled (auto-merge). It distinguishes this function from standard merging.

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 description provides highly nuanced usage guidelines, detailing the precise conditions under which a merge occurs (green CI, checks passed, no pending changes) and how the tool interacts with sibling tools/concepts like the 'merge train' and explicit `merjax_merge_pr` calls.

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