pm.evm

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

Annotations already declare readOnly/idempotent/closed-world, but the description adds real behavioral context: values are Decimal strings in a shared currency unit, results are returned at Decimal division precision with no rounding, pv/ac of zero produce an error, bac must be positive, and EAC assumes current cost efficiency persists. The 'etc_' key naming caveat is a nice touch that prevents a downstream key-lookup mistake.

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?

Front-loaded with the purpose, then the formula block, then input format and constraints, then the EAC assumption caveat — a logical order with no filler. Slightly dense: the formula enumeration may partly duplicate what the output schema already declares, and the etc_ naming note reads as a footnote.

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 4-parameter pure calculator with an output schema and full annotations, the description covers what the schema cannot: units, precision, validation rules, and a modeling assumption behind EAC. The only missing piece is guidance on when to prefer this over pm.earned_schedule.

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 0% (titles only, e.g. 'Pv'), so the description carries the burden and does: all four params are same-currency Decimal strings, pv/ac must be non-zero, bac must be positive. It falls short of expanding the acronyms (PV=planned value, EV=earned value, AC=actual cost, BAC=budget at completion) explicitly, but the formula list makes the roles recoverable.

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?

States a specific verb and resource ('획득가치관리(EVM) 지표를 계산한다') and enumerates the exact indices produced (SPI, CPI, SV, CV, EAC, ETC, VAC), so the agent knows precisely what the tool returns. It never names or contrasts with the nearby pm.earned_schedule or pm.pert siblings, leaving differentiation to inference.

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?

Usage is implied by the formulas (call it when you have PV/EV/AC/BAC and want standard EVM indices), and the non-zero pv/ac and positive bac constraints hint at prerequisites. There is no explicit when-to-use statement and no routing against pm.earned_schedule or other pm.* tools, so the agent must decide on its own.

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