diagnose_cascade

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

Description discloses behavioral traits beyond annotations: 'Pure local math — no network, no submission.' Details what checks are performed and output includes severity and impact. No contradiction with readOnlyHint and idempotentHint.

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?

Description is informative and well-structured, front-loading the main purpose. Slightly verbose with enumerated checks, but each sentence adds value and no redundancy. Appropriate for 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?

Completeness is high: single parameter fully described, output schema exists but description still summarizes output (ranked list with severity, findings, recommendations, Υ impact). Context of usage relative to siblings is clear. No gaps.

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 coverage is 100%, so baseline 3. Description adds value by explaining format details ('Token pillars — ccusage JSON or "input output cacheCreate cacheRead" (same format as rank_paste)') and reinforces acceptable inputs, going beyond schema description.

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?

Description clearly states it analyzes token cascade and diagnoses efficiency leaks with specific checks (cache leverage, velocity, SNR, etc.). Distinguishes from sibling tools (simulate_change) by explicitly specifying order of use.

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?

Explicitly states when to use: 'Use this BEFORE simulate_change to understand what's wrong, then use simulate_change to test fixes.' Also notes it accepts same input format as rank_paste, providing clear context for usage.

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