rank_windows

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

Annotations already indicate readOnlyHint and idempotentHint, but the description adds important behavioral traits: independent parsing per window, no submission capability, and partial input allowance. 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 dense but well-structured with critical information front-loaded. A minor redundancy (e.g., 'from a dashboard paste' could be shortened) prevents a perfect score.

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 complexity of multi-window ranking, the gotcha, and partial input, the description covers all essential context. An output schema exists (mentioned in signals), so return values need no explanation. Completeness is excellent.

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%, yet the description adds significant meaning: required named keys, positional unsafety, partial input flexibility, and purpose of source_tool. The gotcha warning is especially valuable.

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 ranks all four time windows from a dashboard paste, computing cascade metrics per window. It distinguishes from the sibling tool 'tokenpull_submit' by explicitly 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?

Explicitly states when to use (having a paste from cusage/tokscale/etc.), provides a crucial gotcha about positional order, and directs to tokenpull_submit for publishing. Full guidance on partial input is also given.

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