suggest_improvements

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

Annotations already indicate readOnlyHint=true and idempotentHint=true, but the description adds significant behavioral context beyond these: 'Pure local math — no network, no submission.' It also describes the internal simulation and ranking process, and the output structure. 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 well-structured: it starts with a concise summary of the tool's purpose, then details the process and output, and ends with usage guidance. It is informative but slightly verbose; a few sentences could be trimmed without losing essential information.

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 tool's complexity, the description is remarkably complete. It covers the input format, the improvement strategies tested, the simulation engine, the ranking by Υ yield, the output details, and the usage sequence relative to sibling tools. The presence of an output schema (not shown) reduces the burden on the description, but the description still provides ample context.

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% with one property 'text' described as 'Token pillars — ccusage JSON or "input output cacheCreate cacheRead" (same format as rank_paste).' The description adds value by clarifying it requires the 4 pillars and explaining the format, thus going beyond the schema alone.

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 explicitly states it generates ranked simulated improvement suggestions for a token cascade. It specifies the input (4 pillars), the process (multiple strategies, simulation with canonical cascade engine), and the output (ranked suggestions including best_single_change). It distinguishes itself from siblings by referencing the sequence: use after diagnose_cascade and before simulate_change.

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 clear usage context: 'Use this after diagnose_cascade to get actionable next steps, then use simulate_change to fine-tune before committing.' It also notes the tool accepts the same input formats as rank_paste. However, it does not explicitly state when not to use it or list alternatives beyond the referenced siblings.

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