downtime_events

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the read-only nature is covered. The description adds substantial behavioral detail: the keyword heuristic categorization logic, the effect of min_duration_s as a filter, and the exact structure of returned events. The [READ][risk=low] tag further reinforces safety expectations. No contradiction with annotations.

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 well-organized into Summary, Args, Returns, and Example sections. Each sentence provides essential information, and the core purpose is front-loaded. Despite being longer than typical descriptions, it justifies its length given the tool's complexity and the absence of an output schema.

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 3-parameter tool with no output schema, the description is fully complete. It defines all inputs, the output structure (including nested by_category and events), the category mapping behavior, and gives a concrete example. An agent has all necessary information to invoke the tool correctly without additional assumptions.

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 0%, so the description carries the full burden. It thoroughly explains each parameter: series format (ISO-8601 timestamps, state types including string/bool/number), category_map as an optional override with default heuristic behavior, and min_duration_s as a filter. This goes well beyond the schema's bare names and types.

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+resource: 'Detect running→stopped transitions and categorize stoppages.' This clearly states the tool's function and distinguishes it from sibling tools like downtime_root_cause or oee_compute. The additional example and return structure reinforce the purpose.

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 clearly implies when to use the tool: when you need to identify and categorize downtime events from timestamped state data. However, it does not explicitly name alternatives or exclusions. The precise input/output specification gives enough context for an agent to infer appropriateness, but lacks explicit comparison to other downtime-focused tools.

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