suggest_improvements

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

Annotations provide readOnlyHint, idempotentHint, and openWorldHint. The description adds 'Pure local math — no network, no submission' confirming no side effects, and describes the simulation process and output structure. 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 detailed but relatively concise for the complexity. It front-loads the core purpose ('Generates ranked... suggestions'), then lists strategies and return fields. Every sentence adds value, though a slight trimming of repetitive details could make it more efficient.

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 presence of annotations and an output schema, the description provides sufficient context: it explains the input format, simulation strategies, return structure (including best_single_change), and confirms no side effects. Complete enough for an AI agent to use correctly.

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 100% and already documents the 'text' parameter as 'Token pillars — ccusage JSON or...'. The description adds minimal extra value by cross-referencing rank_paste format, but this does not significantly enhance understanding beyond the schema.

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 uses the specific verb 'generates' and resource 'ranked...improvement suggestions' for a token cascade. It clearly distinguishes from sibling tools by specifying when to use (after diagnose_cascade, before simulate_change) and mentioning input format link to rank_paste.

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 'Use this after diagnose_cascade to get actionable next steps, then use simulate_change to fine-tune before committing.' Also mentions it accepts same input as rank_paste, providing clear context and ordering with siblings.

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