rank_windows

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

The description aligns with annotations (readOnlyHint, idempotentHint) by confirming it does not submit and each window is parsed and scored independently. It also discloses important behaviors: partial input allowed, the gotcha about window ordering, and the source_tool parameter for tracking. 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 concise (4 sentences) and front-loaded with the main purpose. Each sentence adds essential information: purpose, parsing behavior, input format gotcha, and exclusion of submission. No superfluous content; it efficiently conveys all critical details.

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 an output schema (not shown but stated), the description does not need to detail return values. It conceptually describes the output ('cascade, metrics') and covers input flexibility (1-4 windows, partial input allowed). The complexity is well-addressed with warnings and alternatives, making it complete for the tool's 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%, and the description adds significant value beyond the schema by explaining the nature of input (dashboard paste or JSON), the requirement for named keys and why, the gotcha about window ordering, and the purpose of the source_tool parameter (cross-tool variance tracking). This enriches the semantic understanding for the agent.

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 states the tool's purpose: to rank all four time windows from a dashboard paste and return cascade metrics for each window. It uses specific verbs ('rank', 'get the cascade') and resources ('time windows', 'dashboard paste'). It also distinguishes itself from sibling tools like tokenpull_submit by stating it does not submit to the board.

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?

Provides explicit guidance on when to use the tool (when you have a dashboard paste and want analysis for all windows), when not to use it (for submission, use tokenpull_submit), and important input format warnings (named keys required, positional order is unsafe). This clearly differentiates its usage from alternatives.

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