rank_windows

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

With no annotations, the description must disclose behavior. It explains that each window is parsed independently, named keys are required, partial input is allowed, and the tool does not submit to the board. It lacks an explicit statement about being read-only or non-destructive, but the context implies it.

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 and front-loaded with the core purpose, followed by key details (partial input, named keys, gotcha). It earns each sentence and does not waste words, though it could be slightly more streamlined.

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 no output schema, the description mentions the cascade metrics returned but does not detail the exact output format. It covers the gotchas, parameter types, and intended use, making it fairly complete for a complex 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?

Schema coverage is 100%, but the description adds value: it explains the independent scoring of windows, the requirement for named keys, the gotcha about positional order vs named keys in dashboards, and the source_tool parameter for tracking. This goes beyond the schema's descriptions.

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: ranking all four time windows from a dashboard paste. It specifies the source tools (ccusage, tokscale, Claude Max) and the output cascade metrics (Υ, SNR, Leverage, etc.). This distinguishes it from siblings like 'tokenpull_submit' which submits 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?

Explicit guidance is provided: omit windows not available (partial input allowed, 1–4 windows), use named keys due to positional gotcha, and note that this tool does not submit to the board; for that use 'tokenpull_submit'. This helps the agent decide when to use this tool.

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