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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior. The description goes well beyond that by disclosing the null-handling contract, the refusal to guess zeros or a default currency, the needs_input response with no estimate, and the scope limit that it does not read an ad account or change a budget. This is rich behavioral disclosure beyond structured fields.

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 purpose is front-loaded and the critical input-handling rules follow in a logical order. However, there is some repetition: 'Ask for missing inputs even if asked not to ask questions' is restated by the needs_input sentence, and 'Unknown fields must be null, never guessed zeros' overlaps with 'Only explicit user-supplied zeros are valid.'

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 financial calculator with seven required parameters, an output schema, and full annotation coverage, the description covers the essential contract: what it computes, how unknown inputs are handled, the return state when inputs are missing, and its read-only scope. The output schema can carry return-value details, so no important agent-facing behavior is missing.

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 schema already documents every parameter thoroughly, including units, null semantics, and the 3-means-3% rule. The description adds a general cross-parameter rule about nulls and explicit zeros, but nothing about individual parameter syntax or meaning that the schema does not already provide. Baseline 3 is appropriate.

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 states a specific verb and resource: calculate break-even and target-profit ROAS plus maximum CPA from user-supplied inputs. It is clear what the tool does, but it never distinguishes itself from the sibling compare_profit_scenarios or any other alternative, so sibling differentiation is absent.

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 gives strong conditional rules for missing inputs ('Ask for missing inputs even if asked not to ask questions', 'If any input is unknown, returns needs_input'), which is useful invocation context. However, it does not say when to choose this tool over siblings such as compare_profit_scenarios or when not to use it, leaving alternative selection implied at best.

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