Miyabi MCP Bundle

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

With no annotations provided, the description carries full burden but offers minimal behavioral disclosure. 'List' implies a read operation, but it doesn't specify whether this requires elevated permissions, what format the output takes, whether it includes real-time tracking or historical data, or how 'Track spawned subprocesses' actually works. For a system monitoring tool with zero annotation coverage, this leaves critical behavioral aspects undocumented.

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 extremely concise with two clear sentences that directly address the tool's function. Every word earns its place - 'List child processes' establishes the core action, 'of a parent PID' specifies the scope, and 'Track spawned subprocesses' adds important behavioral context. No wasted words or redundant phrasing.

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 system process monitoring tool with no annotations and no output schema, the description is insufficient. It doesn't explain what information is returned about child processes (PID, name, status, etc.), how the tracking functionality works, whether this is a one-time snapshot or continuous monitoring, or any error conditions. The agent would need to guess critical behavioral aspects.

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?

Schema description coverage is 100% with the single parameter 'pid' clearly documented as 'Parent process ID'. The description adds marginal value by reinforcing this is for 'child processes of a parent PID', but doesn't provide additional context about PID format, valid ranges, or how to obtain parent PIDs. With complete schema coverage, the baseline 3 is appropriate.

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 with specific verbs ('List', 'Track') and resource ('child processes of a parent PID'). It distinguishes from siblings like 'process_list' (general listing) and 'process_tree' (hierarchical view) by focusing on direct children of a specific PID. However, it doesn't explicitly differentiate from 'process_search' which might also find child processes.

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 no guidance on when to use this tool versus alternatives. It doesn't mention when to choose this over 'process_tree' (which shows hierarchical relationships) or 'process_list' (which lists all processes). No prerequisites, exclusions, or complementary tools are specified.

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