company_what_if

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

With no annotations, the description carries the transparency burden and does so well. It explicitly declares 'Read-only', states that it is arithmetic on recorded books rather than a forecast, and details exactly what it returns (ladder before/after, operating result change, break-even, cash, payback, assumptions). It also explains the build vs compare behaviors. It doesn't mention auth or rate limits, but for a read-only internal tool those are secondary.

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 dense but every sentence earns its place. It front-loads the core purpose, then compactly enumerates levers and their fields, then lists outputs and operations, and closes with the safety/scope statement. The telegraphic style efficiently conveys a large amount of information without fluff.

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?

The domain behavior and return contents are well covered, and an output schema exists for return values. However, the input mechanics are incomplete: the 7 schema parameters (now, engine, operation, entity_ref, project_id, bundle_json, payload_json) are mostly unexplained, and the detailed lever syntax is not connected to how it should be passed. For a tool with 0% schema coverage and 7 parameters, this is a meaningful gap.

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 0%, so the description must compensate. It richly explains the domain-level levers (price, volume, hire, contractor, customer, cost_line, payment_terms) and their sub-fields. However, it never maps these levers to the actual schema parameters (bundle_json, payload_json, entity_ref, etc.), and the required project_id is not mentioned at all. An agent still cannot determine where scenario_ref and levers go in the request 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 is specific and distinct: 'the exact consequence of a decision on the books' ladder' clearly defines a verb (compute consequence) and resource (books' ladder). It differentiates itself by explicitly stating it is 'Arithmetic on the recorded books, not a forecast', which separates it from forecasting/simulation siblings like company_simulate or company_cash_calendar. The operation sub-modes (build vs compare) further clarify its role.

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 clear context for when to use this tool: to evaluate decisions on the books' ladder using specific levers. It also provides a boundary with 'not a forecast', helping an agent choose between this and forecasting tools. However, it doesn't explicitly name alternative tools or state 'use X instead', so the exclusion is implied rather than explicit.

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