program_device

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

The description goes beyond destructiveHint/openWorldHint by explaining exactly which modes are volatile ('lost at power-off') versus persistent and destructive ('overwrite what the board boots from'). This is concrete, decision-relevant behavior that annotations alone do not convey.

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?

Bullet-style mode lines front-load the core semantics, and every sentence adds operational value. No filler or repetition.

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 9-parameter, destructive, no-output-schema tool, the description covers the important decision points and warnings. The only notable gap is not describing what the call returns or how wait_seconds/verify_method affect execution, but the core usage is complete.

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?

With 0% schema coverage, the description compensates well by explaining all mode variants, the project/file mutual exclusion, cable-selection parameters, and chain_device_number. It does not fully explain wait_seconds, jtag_clock_hz, or verify_method, so it is helpful but not exhaustive.

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 first line names a specific verb ('Program'), resource ('Efinix FPGA'), and mechanism ('Efinity command-line programmer'). The mode breakdown further differentiates it from sibling management/query tools such as list_programmer_cables or run_flow.

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 clear mode-selection guidance (JTAG vs flash vs bridge), instructs when to confirm with the user, and points to list_programmer_cables for cable selection. It stops short of explicitly stating which sibling tools should be used instead for non-programming workflow steps, but the context is strong.

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