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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds value by stating 'Parameters are processed remotely without application persistence,' clarifying no state is stored. It also explicitly notes the worksheet does not establish Sybil resistance or distribute tokens, which are important limitations not captured by annotations. This goes beyond what annotations provide, so a 4 is appropriate.

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 well-structured with a clear lead sentence stating the core function, followed by limitations and usage hints. It is moderately concise, though the list of exclusions ('No live subnet data, fraud detection, Bittensor emission replication, staking recommendation or token distribution') is a bit redundant. Overall, it is efficient and front-loaded.

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 calculation tool with an output schema, the description adequately covers purpose, limitations, and input sourcing. It mentions how to obtain exact inputs (via fetch or example resource) and clarifies it is a worksheet without persistence. While it does not detail output structure, that is covered by the output schema. It lacks explicit when-to-use guidance, but given the exclusions and clear scope, it is reasonably complete.

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%, so all parameters are described. The description adds relational meaning by explaining that customerRevenue and tokenSubsidy are separated, and that budget is allocated using 'accepted work and quality weights'—tying to contributors' acceptedTasks and quality fields. It also mentions 'Contributor caps' (capPercent) and 'exact budget conservation,' which clarifies how budget is handled. This exceeds the literal schema descriptions, warranting a 4.

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 function: it separates customer revenue from token subsidy and allocates a declared reward budget based on accepted work and quality weights. It also lists specific exclusions (no Sybil resistance, no token distribution) that distinguish it from sibling tools like those handling live subnet data or fraud detection. The purpose is unambiguous and the resource (Incentive Lab) is named.

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 provides implicit usage guidance through exclusions (e.g., 'No live subnet data, fraud detection, Bittensor emission replication') but does not explicitly state when to use this tool versus alternatives. It mentions retrieving inputs via fetch or reading an example resource, but this is about input sourcing, not tool selection. There is no explicit 'use this when...' guidance, so the guidance is implied but not fully actionable.

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