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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely new behaviour: deterministic output, no programme lookup, no simulation, and that calculation inputs and results are not logged – a privacy-relevant trait an agent cannot get from the annotations. It stops short of saying how assumptions and limitations are surfaced.

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?

Three compact sentences, front-loaded with the purpose before units, returns, exclusions and logging. 'Rates use percentages (35 means 35%), money uses currency units' partly duplicates nested schema text, but it is short and reads as a deliberate global convention rather than 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 nested, calculation-only tool with no output schema, the description covers what comes back (exact commission strings, rounded monthly engine inputs, assumptions and limitations) and where the inputs must come from. Remaining ambiguity is mainly about the returned 'assumptions and limitations' shape and the banded/hybrid mode combinations the engine selects.

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?

Top-level schema coverage is reported as 0%, so the description carries burden, and it does supply the critical unit convention: percentages as 35 meaning 35%, and money in currency units. The nested properties are themselves thoroughly documented, and the description does not otherwise explain the required players/deal structure. Unit conventions are the main gap it fills, and they are also present in nested field 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?

Uses a specific verb (project) with a precise resource scope: monthly CPA, revenue-share and hybrid commission, driven by supplied player behaviour and deal terms. The 'deterministic' qualifier signals it is a pure calculation. It does not, however, distinguish itself from the plausible sibling calculate_affiliate_commission, so an agent seeing both still has to guess.

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?

'from explicitly supplied player behaviour and deal terms' establishes the precondition for use, and 'Does not look up programmes or perform simulation' is an explicit when-not boundary that rules out lookup-style tools. No alternative is named by name, so routing between this and calculate_affiliate_commission remains an inference.

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