voltage_doctor

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

The annotations already declare readOnlyHint=true and openWorldHint=false, establishing a safe, closed-world read operation. The description adds valuable context beyond safety: it lists the specific components checked (session type, input-device permissions, capture backends, screen geometry, GPU memory vs model profile, both model backends) and states that it returns fix commands. This informs the agent about the scope of the check and the nature of the response, which is more than annotations provide. No contradiction found.

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 description is three sentences, tightly packed with information. The first sentence gives the core purpose, the second enumerates the checks and the fix-command behavior, and the third provides usage timing. Every sentence earns its place, and the most important information (purpose and when to use) is front-loaded. There is no fluff or redundancy.

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 no-argument diagnostic tool, the description is comprehensive. It clearly states what is checked, the response characteristic (returns fix commands), and when to call it. An output schema exists (though not shown), so the description doesn't need to detail return formats. Given the complexity of the checks and the existence of a schema, nothing essential is missing for the agent to use the tool correctly.

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 tool has zero parameters and the schema shows none. The description implicitly confirms this by stating 'Call this before the first run on a machine' with no mention of inputs. Since there are no parameters to explain, the description effectively communicates that it requires no configuration. This is a perfect fit for the no-parameter case, and the baseline of 4 is exceeded because the description makes the absence of parameters obvious.

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 clearly states the tool's purpose: 'Check that everything needed for a run is present and working.' It specifies a concrete action (check) and a distinct resource (run prerequisites). It differentiates from siblings like voltage_status and voltage_diagnose by enumerating the exact checklist items (session type, permissions, capture backends, geometry, GPU memory, model backends). This makes it unambiguous which tool to select for pre-flight validation.

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 gives explicit timing guidance: 'Call this before the first run on a machine.' While it doesn't mention alternatives or when not to use it, the instruction is clear and actionable. It implies this is a single-use setup check, not a repeated monitoring tool. The guidance is sufficient for the agent to decide when to invoke it, though lacking explicit exclusions.

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