peerglass_shutdown_detect

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

Excellent disclosure beyond annotations. While annotations declare readOnly/idempotent hints, the description explains the critical stateful behavior (baseline storage between calls), the exact severity classification thresholds (5%, 20%, 80%), and the return value composition. 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?

Well-structured with clear sections. The severity level bullet points efficiently communicate complex thresholds. Every sentence serves a purpose—explaining mechanism, state management, or parameter formats. No redundant or filler text.

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?

Very complete for a detection tool with stateful behavior. Explains the baseline mechanism, severity levels, and return format. Minor gap: could mention `peerglass_shutdown_timeline` as a complementary tool for users needing historical data rather than current detection.

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?

Despite the schema having minimal coverage (country_code only partially described), the description fully compensates by documenting both parameters with concrete examples ('SY', 'IR', 'MM') and clarifying the response_format default and options ('markdown' vs 'json') that the schema lacks.

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 specific action (detect internet shutdowns), the resource (country-level), and the mechanism (BGP prefix comparison against baseline). It distinguishes this from generic monitoring tools by specifying the BGP/withdrawal methodology.

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?

Provides critical usage context about the stateful nature (first call establishes baseline, subsequent calls measure) and explains the severity classification thresholds. However, it does not explicitly mention sibling tools like `peerglass_shutdown_timeline` as an alternative for historical analysis vs. current detection.

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