factory_health

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals measurement methodology (fixed 300-second window), defines uptime, explains every state in detail including non-obvious causes (e.g., 'dead node' from game updates), and gives a critical interpretation caveat about 'blocked' states. This is exemplary transparency beyond what structured fields could 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?

The description is dense but well-structured: a one-sentence summary, a short measurement basis, a scannable list of states with parenthetical explanations, and a bold final caveat. Every sentence earns its place, with no fluff or repetition. The format aids quick comprehension despite the complexity of the domain.

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 that there is no output schema, the description adequately conveys the key output dimensions (uptime per machine and reason for stopped machines) and enumerates all possible states. It misses explicit return format details (e.g., how limit or factory filtering affects rows), but for a diagnostics tool with rich state semantics, it is nearly complete. Sibling-tool context reinforces its role.

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 adds no information about the parameters (save, limit, world, factory) beyond what the schema already provides. Schema coverage is only 50% (save and world lack descriptions), and the description does not compensate by explaining them or their roles in the query. The only indirect relevance is 'per machine,' but that does not clarify parameter semantics.

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: 'Measured uptime per machine, and WHY each stopped one is stopped.' It immediately distinguishes this tool from siblings by claiming 'The only measured numbers in this MCP.' This clearly identifies the tool's unique purpose, making it easy for an agent to know exactly what it does.

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 does not explicitly name alternatives or state when-not-to-use. However, it provides interpretive guidance on which states are actionable ('Blocked is not automatically a fault... Starved, stalled and no-recipe are the actionable ones'), implying the tool is for diagnosing actionable factory health issues. This is useful but lacks explicit comparison to sibling tools like factory_query.

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