rank_paste

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true. The description adds crucial context beyond annotations: 'runs the full cascade math locally (no network calls)', 'deterministic prose' (idempotency), and error behavior ('Returns an error if the input is malformed or has negative values'). It also discloses the exact metric formulas and stage classification, making the tool's behavior fully transparent. 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 long but densely packed without fluff. It is front-loaded with the core purpose, then systematically covers outputs, input formats, error conditions, and usage guidance. Every sentence adds information, though it could arguably be trimmed slightly; however, for a tool with this complexity and the need to distinguish from siblings, the length is justified. The structure is logical and scannable.

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?

Despite the tool's complexity, the description is entirely self-contained. It covers purpose, usage boundaries, input syntax, output semantics, error handling, local computation, and integration with submit_paste. The output schema is present, yet the description still explains each return field (yield, snr, etc.) and even the classification stages. With one parameter and no nested objects, this is more than complete—it is exceptionally thorough.

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 substantial meaning beyond the schema. It explains both accepted input formats in detail, specifies the order of numbers, clarifies that values must be non-negative integers, and provides a concrete example: '{"input":1000000,"output":500000,"cacheCreate":50000,"cacheRead":800000}'. It also links the parameters to the output metrics (e.g., yield formula), giving the agent a deeper understanding than the schema alone.

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+resource: 'Computes the SigRank yield cascade from a paste of token counts.' It clearly distinguishes from siblings by explicitly naming submit_paste and rank_windows as alternatives, and describes the precise outputs (yield, snr, leverage, velocity, dev10x, class, mode, prose card). This leaves no ambiguity about what the tool does.

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 explicitly states when to use ('Use this for a quick one-off ranking without submitting to the board') and when not to use it, naming two alternatives: 'Do NOT use this to submit your score — use submit_paste instead' and 'Do NOT use this if you want to rank all four time windows at once — use rank_windows for that.' It also advises calling submit_paste afterward to publish. This is exemplary usage guidance with concrete exclusions and alternatives.

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