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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context: payer-before-recipient computation order, how connected-dividend Part IV is filled in from the payer's refund, the return summary, and a concrete pricing model with a cap and free members. Nothing contradicts the 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?

Three dense sentences, each earning its place: purpose and computation behavior, return contents and differentiator, and pricing model. The main verb and resource are front-loaded, and there is no filler or redundant restatement of the schema.

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 complex multi-member tax computation with no output schema, the description summarizes the return (member lines, group grind cost, and the member causing it) and the key cascade behavior. The detailed input schema carries the parameter burden; the description provides enough operational context for an agent to invoke the tool correctly, though exact output fields are not enumerated.

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%, so the baseline is 3, but the description adds meaning beyond the schema by explaining how parameters relate: member prior-year AAI feeds federal line 417, businessLimitAllocated feeds the Schedule 23 allocation, and payerId in dividendsReceivedConnected drives the payer-before-recipient cascade. It also clarifies that members contributing only line 417 are free, which maps to the members array structure.

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 and resource: 'Compute a whole associated group (s.256) in one call.' It lists the exact computations involved (line 417, Schedule 23 allocation, Part IV cascade) and contrasts with 'a single-corporation computation,' which helps distinguish it from the sibling resolve tool.

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 clearly signals when to use the tool: when a whole associated group must be computed, especially with connected dividends that require payer-before-recipient ordering. It implies the alternative of a single-corporation computation by saying this is the case a single-corporation computation cannot show, though it does not explicitly name the sibling tools.

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