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

The description adds behavioral context beyond the readOnlyHint annotation: it says the tool operates 'deterministically' and 'with no generative model in the path,' which sets clear expectations about the nature of the output. It also clarifies that the 'question' field is optional and does not drive the answer—only facts do. 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 information-dense but every sentence carries weight—initial action, specific rules, usage scenarios, and sibling pointer. The list of topics is long but directly relevant; it avoids fluff and extra verbiage, though slightly longer than strictly necessary.

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?

Given the high complexity of Indian TP rules, the description covers the tool's core functionality, its deterministic nature, the types of questions it answers, and an explicit alternative. Even though there is no output schema, the enumeration of what it calculates (safe harbour, methods, tested party, arm's-length range) effectively communicates expected results. This is a complete and self-sufficient description.

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 56%, and the description does not directly map to individual parameters beyond broad references (e.g., 'safe-harbour eligibility' implies serviceMarkupPct). The input schema already provides descriptions for key params like alrPercentile and transactionType. The description adds marginal context but does not clarify less-documented parameters such as posture or hasExternalCup, so it lands at the baseline.

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 uses a specific verb ('screen') plus a clear resource ('Indian transfer-pricing position') and enumerates concrete outputs (safe-harbour eligibility, documentation obligations, eligible methods, tested-party rule, arm's-length range). It also distinguishes itself from the sibling tool analyze_cross_border_tax, 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?

Explicitly states when to use this tool ('Use for questions about intra-group service fees, cost-plus markups, royalties, management charges...') and provides an explicit alternative for the PE side ('use analyze_cross_border_tax'). This is textbook usage guidance.

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