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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior. Beyond that, the description discloses the exact rounding formula (half-up hundredths), which tells the agent the operation is a pure deterministic computation with no hidden lookups or side effects.

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?

Two sentences, purpose front-loaded, followed by the exact formula and a single disambiguating clause. No filler; every element earns its place.

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?

There is no output schema, but the embedded formula tells the agent precisely what numeric result to expect, so the return value is effectively covered. For a two-input pure calculator this is nearly complete, with only parameter units (e.g., currency) left implicit.

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?

With 0% schema description coverage, the description must carry parameter meaning, and it does: 'rent' is specified as monthly (annualized via *12 in the formula), and 'value' is clarified as a user-supplied figure rather than a looked-up price. It stops short of stating types or units for value, but the added semantics are substantive.

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 computation (gross yield) over specific inputs (monthly rent and value) and explicitly distinguishes itself from the sibling lookup_gross_yield by noting 'It does not look up a price.' An agent can pick between the calculate_* and lookup_* tools without reading further.

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 monthly rent and value you pass' plus 'It does not look up a price' tells the agent to use this when it already holds both inputs, routing away from the lookup variant. It gives clear context but never names the alternative tool explicitly, leaving the routing inference one step short of explicit.

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