Miyabi MCP Bundle

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

No annotations are provided, so the description carries full burden. While 'Get warning-level log entries' implies a read operation, it doesn't disclose important behavioral traits: whether this requires specific permissions, how results are formatted (structured vs raw), if there's pagination or limits, what happens when no warnings exist, or if the tool performs any filtering beyond warning level. The description adds minimal behavioral context beyond the basic operation.

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 appropriately concise with two sentences that each serve a purpose. The first sentence states the core functionality, and the second adds value context about finding potential issues. There's no wasted language, though it could be slightly more structured by explicitly mentioning the optional time filtering parameter.

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 tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what format the warnings are returned in, whether they include timestamps/sources/severity details, how many results are returned, or what happens when the optional parameter isn't provided. The description leaves too many behavioral questions unanswered for a tool that presumably returns structured log data.

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% (the 'minutes' parameter is fully documented in the schema), so the baseline is 3. The description doesn't add any parameter-specific information beyond what the schema provides. It doesn't explain default behavior when minutes isn't specified, typical values, or how the time filtering interacts with the warning-level filtering.

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: 'Get warning-level log entries' specifies the verb (get) and resource (warning-level log entries). It distinguishes from siblings like log_get_errors (errors) and log_get_recent (recent entries of all levels), but doesn't explicitly differentiate from log_search which could also retrieve warnings. The 'Find potential issues before they become errors' adds useful context about the tool's value.

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 log_get_warnings over log_get_errors, log_get_recent, or log_search. The sibling tool list shows multiple log-related tools, but the description offers no comparative context or prerequisites for usage.

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