rank_windows

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

Annotations already indicate read-only and idempotent, but the description adds critical behavioral disclosures: each window is parsed/scored independently, positional order is unsafe (dashboards list cache_read before cache_create), and the tool does not publish/submit. This goes well beyond the structured hints and gives the agent a full behavioral picture.

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 every sentence delivers essential guidance: purpose, input sources, output, parsing behavior, key requirements, partial-input allowance, and interaction with a sibling tool. It is front-loaded with the core purpose and then logically layers caveats without any 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?

For a tool with five parameters, a complex input format, and an output schema, the description covers all necessary aspects: what it does, how to invoke it, gotchas, and relationship to alternatives. The presence of an output schema means return-value details are unnecessary, and the description fills the remaining gaps perfectly.

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?

Although the schema already describes each window parameter as a paste/JSON string, the description adds crucial semantics: the required named keys (input/output/cacheCreate/cacheRead), the warning against positional order, and that partial windows are allowed. This transforms the parameters from simple strings into well-specified structured inputs.

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 opens with a specific verb ('Rank') and resource ('all four time windows'), clearly stating the tool's function and inputs (dashboard paste). It distinguishes itself from siblings by explicitly noting it does NOT submit to the board and pointing to tokenpull_submit for that, making its purpose unambiguous.

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 gives explicit when-to-use context: for ranking all four time windows from a single paste, with source tools named (ccusage, tokscale, Claude Max). It also provides exclusions—'Does NOT submit to the board'—and directs to tokenpull_submit as the alternative, plus practical guidance on partial input and the named-keys requirement.

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