diagnose_cascade

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

Even with readOnlyHint/idempotentHint annotations, the description adds meaningful behavioral context: 'Pure local math — no network, no submission' and describes output structure (ranked leaks, severity, findings, recommendations, estimated impact).

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 long but every sentence serves a purpose: purpose, checks performed, output details, and safety caveat. It is front-loaded and well organized for a complex analysis tool.

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?

Given the output schema exists, the description need not detail return values, but it still covers what checks are performed, output type (ranked list with severity/findings/recommendations), and the local/no-submission behavior, making it complete.

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 already documents the 'text' parameter at 100% coverage, so baseline is 3. The description adds value by specifying 'JSON or 4 whitespace numbers' and noting it accepts the same format as rank_paste, clarifying the expected input forms.

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 ('Analyzes your token cascade and diagnoses where you're leaking efficiency') and names the resource. It distinguishes from siblings by positioning it as the pre-simulation diagnostic and referencing rank_paste's input format.

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?

Explicit usage guidance: 'Use this BEFORE simulate_change to understand what's wrong, then use simulate_change to test fixes.' This clearly tells the agent when to invoke this tool relative to alternatives.

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