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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds substantive behavioral context: default UTC interpretation, inclusive/exclusive boundaries, overlap filtering, and tz parameter behavior. It explains exactly how the time window is interpreted, which is non-obvious and valuable. No contradictions 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 compact, with the core purpose stated first and timezone details separated in a code block. It uses concise syntax (backticks for parameters) and avoids fluff. The structure front-loads the essential semantics, making it easy to scan. It is slightly dense but appropriately sized for the complexity.

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 6-parameter tool with 0% schema coverage, the description is incomplete. It thoroughly covers the time window behavior but omits explanations for `kind` and `min_mw`, which are not self-evident. The output schema exists, so return format is covered, and annotations cover safety. However, the missing parameter semantics leave gaps that an agent would need to infer or probe.

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 must compensate. It explains the semantics of start, end, and tz (inclusivity, exclusivity, overlap, timezone conversion). However, it says nothing about the `kind` parameter (default 'generation') or `min_mw` filter, leaving their meaning entirely to schema field names. The description adds value for time-related params but does not fully compensate for the 0% coverage across all 6 parameters.

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 'Generation-unit unavailability events (UMM)', clearly stating the tool returns generation outage data. The verb 'get' and resource 'outages' are specific, and the title reinforces this. It does not explicitly differentiate from siblings like get_generation or get_load, but the domain of outages is distinct enough that an agent can infer when to use it. A score of 4 reflects clarity without explicit sibling comparison.

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 detailed guidance on timezone handling and window inclusivity (start inclusive, end exclusive, overlap semantics) but offers no guidance on when to choose this tool over alternatives. It never mentions sibling tools like get_generation or get_series, nor states conditions that would favor one over the other. This is a significant gap for a tool with many siblings.

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