add_drop

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

With no annotations, the description carries the full burden. It discloses that the bus argument is a substring of an existing bus name and that drops are populated via later tool calls, but it does not mention side effects, error behavior, or whether the drop is modified in place, created fresh, or subject to validation. The power-supply note is useful domain context, not tool behavior.

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 compact and front-loaded with the core action, then delivers parameter details and workflow in a logical order. The parenthetical examples add clarity without bloat, though the sentence about part_number would benefit from similar treatment, making it slightly denser than necessary.

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 description is adequate for a read of the intended workflow, but it leaves a required parameter unexplained and gives no information about output, validation, or potential failure modes. For a mutation tool in a complex hardware domain, this is a noticeable gap that an agent would have to probe at runtime.

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?

The description explains 'bus' and 'drop' meaningfully, but it omits 'part_number', which is listed as a required argument yet is absent from the schema's properties list. Version is also not explained. With schema coverage effectively low (at least one required parameter undocumented), the description fails to compensate for the most critical 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 description opens with a specific verb and resource: 'Add a drop to a bus', then grounds it with a concrete example (remote X80 EIO drop on an M580 EIO/RIO bus). It also clarifies the bus/drop parameter semantics, which clearly distinguishes this tool from siblings like add_rack and add_io_module by stating the drop is the parent to be populated later.

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 names the follow-up tools ('Then use add_rack and add_io_module to populate it') and provides a prerequisite ('bus is a substring of the bus name from get_hardware'). It also gives a domain caution about remote racks needing their own power supply, which helps the agent decide when and how to invoke the tool correctly.

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