simulate_change

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

Beyond the annotations (readOnlyHint=true, idempotentHint=true), the description discloses key behavioral traits: it runs the canonical cascade on BOTH current and simulated values, returns an exact yield delta (implying deterministic math), and specifically notes 'no network, no submission, pure local math.' This adds meaningful context about what the tool does and does not do.

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 front-loaded with the core purpose, then explains the use case, and finally details the input format. Every sentence earns its place: it explains what the tool does, why to use it, and how to use it. The length is justified given the tool's complexity, and there is no filler.

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?

The description covers the tool's purpose, inputs, outputs (yield delta, class change, per-metric diffs), and constraints (local, read-only, no submission). It also includes a practical example use case. Given the presence of an output schema and a clear input schema, the description is complete enough for an agent to decide when and how to invoke the tool.

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?

The schema already provides full descriptions for both parameters (100% coverage). The description adds value by clarifying that the input format is 'same as rank_paste', giving explicit examples for relative deltas ('{cacheRead: '+50000'}') and absolute values ('{input: 800000}'), and restating the semantics of omitted pillars. This reinforces the schema without being redundant.

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 identifies the tool as a 'what if I changed my token mix?' simulation that computes yield deltas, class changes, and per-metric diffs. It uses a specific verb ('simulate') and resource ('token mix'), and explicitly distinguishes itself from siblings as 'the first PRESCRIPTIVE SigRank tool' and a 'show me the payoff before I do the work' primitive.

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 states when to use it ('before you change your workflow') and provides a concrete example question ('would increasing my cache-read by 50k tokens actually move my class?'). It also signals when not to use it: 'no network, no submission' and 'pure local math', implying it is for analysis only. However, it does not explicitly name alternative sibling tools, so it falls short of a full 5.

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